Update entrypoint (#1013 )

* Update entrypoint. * update comment. * Call each extra arg on its own. * Update loop. * Update extra args. * Use miccah's magic script. * Fix path to bash. * update entrypoint. * Add bash to Dockerfile. * update goreleaser dockerfile.
Rename and export isGitSource (#1016 )
2023-01-11 18:58:05 -08:00 · 2023-01-10 12:51:58 -08:00 · 2023-01-10 09:35:44 -08:00 · 2023-01-09 18:09:58 -06:00 · 2023-01-09 17:30:47 -06:00 · 2023-01-09 17:27:06 -06:00
834 changed files with 7032 additions and 2841 deletions
@@ -44,7 +44,7 @@ jobs:
        with:
          go-version: '1.18'
      - name: Run GoReleaser
-        uses: goreleaser/goreleaser-action@v3
+        uses: goreleaser/goreleaser-action@v4
        with:
          distribution: goreleaser
          version: latest
@@ -23,7 +23,7 @@ jobs:
    - name: Checkout code
      uses: actions/checkout@v3
    - id: 'auth'
-      uses: 'google-github-actions/auth@v0'
+      uses: 'google-github-actions/auth@v1'
      with:
        workload_identity_provider: 'projects/811013774421/locations/global/workloadIdentityPools/github-pool/providers/github-provider'
        service_account: 'github-ci-external@trufflehog-testing.iam.gserviceaccount.com'
@@ -42,7 +42,7 @@ jobs:
    - name: Checkout code
      uses: actions/checkout@v3
    - id: 'auth'
-      uses: 'google-github-actions/auth@v0'
+      uses: 'google-github-actions/auth@v1'
      with:
        workload_identity_provider: 'projects/811013774421/locations/global/workloadIdentityPools/github-pool/providers/github-provider'
        service_account: 'github-ci-external@trufflehog-testing.iam.gserviceaccount.com'
@@ -9,7 +9,7 @@ RUN  --mount=type=cache,target=/go/pkg/mod \
     GOOS=${TARGETOS} GOARCH=${TARGETARCH} go build -o trufflehog .

 FROM alpine:3.15
-RUN apk add --no-cache git ca-certificates \
+RUN apk add --no-cache bash git ca-certificates \
    && rm -rf /var/cache/apk/* && \
    update-ca-certificates
 COPY --from=builder /build/trufflehog /usr/bin/trufflehog
@@ -1,6 +1,6 @@
 FROM alpine:3.15

-RUN apk add --no-cache git ca-certificates \
+RUN apk add --no-cache bash git ca-certificates \
    && rm -rf /var/cache/apk/* && \
    update-ca-certificates
 WORKDIR /usr/bin/
@@ -31,12 +31,72 @@ https://join.slack.com/t/trufflehog-community/shared_invite/zt-pw2qbi43-Aa86hkii
 docker run -it -v "$PWD:/pwd" trufflesecurity/trufflehog:latest github --org=trufflesecurity
 ```

+## Examples
+
+### Example 1: Scan a repo for only verified secrets
+
+Command:
+```
+trufflehog git https://github.com/trufflesecurity/test_keys --only-verified
+```
+
+Expected output:
+```
+🐷🔑🐷  TruffleHog. Unearth your secrets. 🐷🔑🐷
+
+Found verified result 🐷🔑
+Detector Type: AWS
+Decoder Type: PLAIN
+Raw result: AKIAYVP4CIPPERUVIFXG
+Line: 4
+Commit: fbc14303ffbf8fb1c2c1914e8dda7d0121633aca
+File: keys
+Email: counter <counter@counters-MacBook-Air.local>
+Repository: https://github.com/trufflesecurity/test_keys
+Timestamp: 2022-06-16 10:17:40 -0700 PDT
+...
+```
+
+### Example 2: Scan a GitHub Org for only verified secrets
+
+```
+trufflehog github --org=trufflesecurity --only-verified
+```
+
+### Example 3: Scan a GitHub Repo for only verified keys and get JSON output
+
+Command:
+```
+trufflehog git https://github.com/trufflesecurity/test_keys --only-verified --json
+```
+
+Expected output:
+```
+{"SourceMetadata":{"Data":{"Git":{"commit":"fbc14303ffbf8fb1c2c1914e8dda7d0121633aca","file":"keys","email":"counter \u003ccounter@counters-MacBook-Air.local\u003e","repository":"https://github.com/trufflesecurity/test_keys","timestamp":"2022-06-16 10:17:40 -0700 PDT","line":4}}},"SourceID":0,"SourceType":16,"SourceName":"trufflehog - git","DetectorType":2,"DetectorName":"AWS","DecoderName":"PLAIN","Verified":true,"Raw":"AKIAYVP4CIPPERUVIFXG","Redacted":"AKIAYVP4CIPPERUVIFXG","ExtraData":{"account":"595918472158","arn":"arn:aws:iam::595918472158:user/canarytokens.com@@mirux23ppyky6hx3l6vclmhnj","user_id":"AIDAYVP4CIPPJ5M54LRCY"},"StructuredData":null}
+...
+```
+
+### Example 4: Scan an S3 bucket for verified keys
+```
+trufflehog s3 --bucket=<bucket name> --only-verified
+```
+
+### FAQ
+
+ All I see is `🐷🔑🐷  TruffleHog. Unearth your secrets. 🐷🔑🐷` and the program exits, what gives?
+  + That means no secrets were detected
+ Why is the scan is taking a long time when I scan a GitHub org
+  + Unauthenticated GitHub scans have rate limits. To improve your rate limits, include the `--token` flag with a personal access token
+ It says a private key was verified, what does that mean?
+  + Check out our Driftwood blog post to learn how to do this, in short we've confirmed the key can be used live for SSH or SSL [Blog post](https://trufflesecurity.com/blog/driftwood-know-if-private-keys-are-sensitive/)  
+
+
 # What's new in v3?

 TruffleHog v3 is a complete rewrite in Go with many new powerful features.

 - We've **added over 700 credential detectors that support active verification against their respective APIs**.
- We've also added native **support for scanning GitHub, GitLab, filesystems, and S3**.
+- We've also added native **support for scanning GitHub, GitLab, filesystems, S3, and Circle CI**.
 - **Instantly verify private keys** against millions of github users and **billions** of TLS certificates using our [Driftwood](https://trufflesecurity.com/blog/driftwood) technology.


@@ -70,7 +130,7 @@ docker run -it -v "$PWD:/pwd" trufflesecurity/trufflehog:latest github --repo ht
 #### **Apple M1 users**

 The `linux/arm64` image is better to run on the M1 than the amd64 image.
-Even better is running the native darwin binary avilable, but there is not container image for that.
+Even better is running the native darwin binary available, but there is no container image for that.

 ```bash
 docker run --platform linux/arm64 -it -v "$PWD:/pwd" trufflesecurity/trufflehog:latest github --repo https://github.com/trufflesecurity/test_keys 
@@ -87,8 +147,7 @@ Help with setting up this packaging would be appreciated!
 ### 5. Brew

 ```bash
-brew tap trufflesecurity/trufflehog
-brew install trufflehog
+brew install trufflesecurity/trufflehog/trufflehog
 ```

 ## Usage
@@ -101,9 +160,10 @@ TruffleHog has a sub-command for each source of data that you may want to scan:
 - S3
 - filesystem
 - syslog
+- circleci
 - file and stdin (coming soon)

-Each subcommand can have options that you can see with the `-h` flag provided to the sub command:
+Each subcommand can have options that you can see with the `--help` flag provided to the sub command:

 ```
 $ trufflehog git --help
@@ -113,26 +173,19 @@ Find credentials in git repositories.

 Flags:
      --help                     Show context-sensitive help (also try --help-long and --help-man).
-      --debug                    Run in debug mode
-      --version                  Prints trufflehog version.
+      --debug                    Run in debug mode.
+      --trace                    Run in trace mode.
  -j, --json                     Output in JSON format.
      --json-legacy              Use the pre-v3.0 JSON format. Only works with git, gitlab, and github sources.
-      --concurrency=1            Number of concurrent workers.
+      --concurrency=10           Number of concurrent workers.
      --no-verification          Don't verify the results.
      --only-verified            Only output verified results.
+      --filter-unverified        Only output first unverified result per chunk per detector if there are more than one results.
+      --config=CONFIG            Path to configuration file.
      --print-avg-detector-time  Print the average time spent on each detector.
      --no-update                Don't check for updates.
-  -i, --include-paths=INCLUDE-PATHS
-                                 Path to file with newline separated regexes for files to include in scan.
-  -x, --exclude-paths=EXCLUDE-PATHS
-                                 Path to file with newline separated regexes for files to exclude in scan.
-      --since-commit=SINCE-COMMIT
-                                 Commit to start scan from.
-      --branch=BRANCH            Branch to scan.
-      --max-depth=MAX-DEPTH      Maximum depth of commits to scan.
-      --allow                    No-op flag for backwards compat.
-      --entropy                  No-op flag for backwards compat.
-      --regex                    No-op flag for backwards compat.
+      --fail                     Exit with code 183 if results are found.
+      --version                  Show application version.

 Args:
  <uri>  Git repository URL. https://, file://, or ssh:// schema expected.
@@ -209,13 +262,111 @@ repos:
    - id: trufflehog
      name: TruffleHog
      description: Detect secrets in your data.
-      entry: bash -c 'trufflehog git file://. --only-verified --fail'
+      entry: bash -c 'trufflehog git file://. --since-commit HEAD --only-verified --fail'
      # For running trufflehog in docker, use the following entry instead:
-      # entry: bash -c 'docker run -v "$(pwd):/workdir" -i --rm trufflesecurity/trufflehog:latest git file:///workdir --only-verified --fail'
+      # entry: bash -c 'docker run -v "$(pwd):/workdir" -i --rm trufflesecurity/trufflehog:latest git file:///workdir --since-commit HEAD --only-verified --fail'
      language: system
      stages: ["commit", "push"]
 ```

+## Regex Detector (alpha)
+
+Trufflehog supports detection and verification of custom regular expressions.
+For detection, at least one **regular expression** and **keyword** is required.
+A **keyword** is a fixed literal string identifier that appears in or around
+the regex to be detected. To allow maximum flexibility for verification, a
+webhook is used containing the regular expression matches.
+
+Trufflehog will send a JSON POST request containing the regex matches to a
+configured webhook endpoint. If the endpoint responds with a `200 OK` response
+status code, the secret is considered verified.
+
+**NB:** This feature is alpha and subject to change.
+
+### Regex Detector Example
+
+```yaml
+# config.yaml
+detectors:
+- name: hog detector
+  keywords:
+  - hog
+  regex:
+    adjective: hogs are (\S+)
+  verify:
+  - endpoint: http://localhost:8000/
+    # unsafe must be set if the endpoint is HTTP
+    unsafe: true
+    headers:
+    - 'Authorization: super secret authorization header'
+```
+
+```
+» trufflehog filesystem --directory /tmp --config config.yaml --only-verified
+🐷🔑🐷  TruffleHog. Unearth your secrets. 🐷🔑🐷
+
+Found verified result 🐷🔑
+Detector Type: CustomRegex
+Decoder Type: PLAIN
+Raw result: hogs are cool
+File: /tmp/hog-facts.txt
+```
+
+#### Verification Server Example (Python)
+
+Unless you run a verification server, secrets found by the custom regex
+detector will be unverified. Here is an example Python implementation of a
+verification server for the above `config.yaml` file.
+
+```python
+import json
+from http.server import BaseHTTPRequestHandler, HTTPServer
+
+AUTH_HEADER = 'super secret authorization header'
+
+
+class Verifier(BaseHTTPRequestHandler):
+    def do_GET(self):
+        self.send_response(405)
+        self.end_headers()
+
+    def do_POST(self):
+        try:
+            if self.headers['Authorization'] != AUTH_HEADER:
+                self.send_response(401)
+                self.end_headers()
+                return
+
+            # read the body
+            length = int(self.headers['Content-Length'])
+            request = json.loads(self.rfile.read(length))
+            self.log_message("%s", request)
+
+            # check the match
+            if request['hog detector']['adjective'][-1] == 'cool':
+                self.send_response(200)
+                self.end_headers()
+            else:
+                # any other response besides 200
+                self.send_response(406)
+                self.end_headers()
+        except Exception:
+            self.send_response(400)
+            self.end_headers()
+
+
+with HTTPServer(('', 8000), Verifier) as server:
+    try:
+        server.serve_forever()
+    except KeyboardInterrupt:
+        pass
+```
+
+## Use as a library
+
+Currently, trufflehog is in heavy development and no guarantees can be made on
+the stability of the public APIs at this time.
+
 ## Contributors

 This project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].
@@ -239,3 +390,10 @@ We have published some [documentation and tooling to get started on adding new s
 ## License Change

 Since v3.0, TruffleHog is released under a AGPL 3 license, included in [`LICENSE`](LICENSE). TruffleHog v3.0 uses none of the previous codebase, but care was taken to preserve backwards compatibility on the command line interface. The work previous to this release is still available licensed under GPL 2.0 in the history of this repository and the previous package releases and tags. A completed CLA is required for us to accept contributions going forward.
+
+
+## Enterprise product
+
+Are you interested in continously monitoring your Git, Jira, Slack, Confluence, etc.. for credentials? We have an enterprise product that can help. Reach out here to learn more https://trufflesecurity.com/contact/
+
+We take the revenue from the enterprise product to fund more awesome open source projects that the whole community can benefit from.
@@ -8,7 +8,8 @@ inputs:
    required: true
  base:
    description: Start scanning from here (usually main branch).
-    required: true
+    required: false
+    default: ''
  head:
    description: Scan commits until here (usually dev branch).
    required: false
@@ -30,4 +31,5 @@ runs:
    - --branch
    - ${{ inputs.head }}
    - --fail
+    - --no-update
    - ${{ inputs.extra_args }}
@@ -1,5 +1,6 @@
-#!/usr/bin/env ash
+#!/usr/bin/env bash

-# `$*` expands the `args` supplied in an `array` individually
-# or splits `args` in a string separated by whitespace.
-/usr/bin/trufflehog $*
+# Parse the last argument into an array of extra_args.
+mapfile -t extra_args < <(bash -c "for arg in ${*: -1}; do echo \$arg; done")
+
+/usr/bin/trufflehog "${@: 1: $#-1}" "${extra_args[@]}"
@@ -9,63 +9,66 @@ replace github.com/zricethezav/gitleaks/v8 => github.com/trufflesecurity/gitleak
 replace github.com/gitleaks/go-gitdiff => github.com/trufflesecurity/go-gitdiff v0.7.6-zombies2

 require (
-	cloud.google.com/go/secretmanager v1.7.0
+	cloud.google.com/go/secretmanager v1.10.0
 	github.com/Azure/go-autorest/autorest/azure/auth v0.5.11
-	github.com/TheZeroSlave/zapsentry v1.11.0
+	github.com/TheZeroSlave/zapsentry v1.12.0
 	github.com/aws/aws-sdk-go v1.44.83
-	github.com/bill-rich/disk-buffer-reader v0.1.4
+	github.com/bill-rich/disk-buffer-reader v0.1.7
 	github.com/bill-rich/go-syslog v0.0.0-20220413021637-49edb52a574c
 	github.com/bitfinexcom/bitfinex-api-go v0.0.0-20210608095005-9e0b26f200fb
 	github.com/bradleyfalzon/ghinstallation/v2 v2.1.0
 	github.com/crewjam/rfc5424 v0.1.0
-	github.com/denisenkom/go-mssqldb v0.12.2
-	github.com/envoyproxy/protoc-gen-validate v0.6.8
+	github.com/denisenkom/go-mssqldb v0.12.3
+	github.com/envoyproxy/protoc-gen-validate v0.9.1
 	github.com/fatih/color v1.13.0
 	github.com/felixge/fgprof v0.9.3
-	github.com/getsentry/sentry-go v0.13.0
+	github.com/getsentry/sentry-go v0.16.0
 	github.com/go-errors/errors v1.4.2
-	github.com/go-git/go-git/v5 v5.4.2
+	github.com/go-git/go-git/v5 v5.5.2
+	github.com/go-ldap/ldap/v3 v3.4.4
 	github.com/go-logr/logr v1.2.3
 	github.com/go-logr/zapr v1.2.3
-	github.com/go-sql-driver/mysql v1.6.0
+	github.com/go-redis/redis v6.15.9+incompatible
+	github.com/go-sql-driver/mysql v1.7.0
+	github.com/gobwas/glob v0.2.3
 	github.com/golang-jwt/jwt v3.2.2+incompatible
 	github.com/google/go-cmp v0.5.9
 	github.com/google/go-github/v42 v42.0.0
 	github.com/gorilla/mux v1.8.0
-	github.com/h2non/filetype v1.1.3
-	github.com/hashicorp/go-retryablehttp v0.7.1
+	github.com/hashicorp/go-retryablehttp v0.7.2
+	github.com/jlaffaye/ftp v0.1.0
 	github.com/joho/godotenv v1.4.0
 	github.com/jpillora/overseer v1.1.6
 	github.com/kylelemons/godebug v1.1.0
 	github.com/lib/pq v1.10.7
 	github.com/mattn/go-colorable v0.1.13
-	github.com/mattn/go-sqlite3 v1.14.15
+	github.com/mattn/go-sqlite3 v1.14.16
 	github.com/mholt/archiver/v4 v4.0.0-alpha.7
 	github.com/paulbellamy/ratecounter v0.2.0
 	github.com/pkg/errors v0.9.1
-	github.com/razorpay/razorpay-go v0.0.0-20210728161131-0341409a6ab2
-	github.com/rs/zerolog v1.28.0
+	github.com/rabbitmq/amqp091-go v1.5.0
 	github.com/sergi/go-diff v1.2.0
 	github.com/sirupsen/logrus v1.9.0
-	github.com/stretchr/testify v1.8.0
+	github.com/stretchr/testify v1.8.1
 	github.com/tailscale/depaware v0.0.0-20210622194025-720c4b409502
-	github.com/xanzy/go-gitlab v0.73.1
-	go.mongodb.org/mongo-driver v1.10.2
-	go.uber.org/zap v1.23.0
-	golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d
+	github.com/xanzy/go-gitlab v0.77.0
+	go.mongodb.org/mongo-driver v1.11.1
+	go.uber.org/zap v1.24.0
+	golang.org/x/crypto v0.5.0
 	golang.org/x/exp v0.0.0-20221018205818-5c77f4b2bbd7
-	golang.org/x/oauth2 v0.0.0-20220909003341-f21342109be1
-	golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4
-	google.golang.org/genproto v0.0.0-20220920201722-2b89144ce006
+	golang.org/x/oauth2 v0.0.0-20221014153046-6fdb5e3db783
+	golang.org/x/sync v0.1.0
+	google.golang.org/genproto v0.0.0-20221201164419-0e50fba7f41c
 	google.golang.org/protobuf v1.28.1
 	gopkg.in/alecthomas/kingpin.v2 v2.2.6
 	gopkg.in/h2non/gock.v1 v1.1.2
+	sigs.k8s.io/yaml v1.3.0
 )

 require (
-	cloud.google.com/go v0.104.0 // indirect
-	cloud.google.com/go/compute v1.7.0 // indirect
-	cloud.google.com/go/iam v0.3.0 // indirect
+	cloud.google.com/go/compute v1.12.1 // indirect
+	cloud.google.com/go/compute/metadata v0.2.1 // indirect
+	cloud.google.com/go/iam v0.8.0 // indirect
 	github.com/Azure/go-autorest v14.2.0+incompatible // indirect
 	github.com/Azure/go-autorest/autorest v0.11.24 // indirect
 	github.com/Azure/go-autorest/autorest/adal v0.9.18 // indirect
@@ -73,19 +76,22 @@ require (
 	github.com/Azure/go-autorest/autorest/date v0.3.0 // indirect
 	github.com/Azure/go-autorest/logger v0.2.1 // indirect
 	github.com/Azure/go-autorest/tracing v0.6.0 // indirect
-	github.com/Microsoft/go-winio v0.4.16 // indirect
-	github.com/ProtonMail/go-crypto v0.0.0-20210428141323-04723f9f07d7 // indirect
+	github.com/Azure/go-ntlmssp v0.0.0-20220621081337-cb9428e4ac1e // indirect
+	github.com/Microsoft/go-winio v0.5.2 // indirect
+	github.com/ProtonMail/go-crypto v0.0.0-20221026131551-cf6655e29de4 // indirect
 	github.com/acomagu/bufpipe v1.0.3 // indirect
 	github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751 // indirect
 	github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 // indirect
 	github.com/andybalholm/brotli v1.0.4 // indirect
 	github.com/benbjohnson/clock v1.1.0 // indirect
+	github.com/cloudflare/circl v1.1.0 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/dimchansky/utfbom v1.1.1 // indirect
 	github.com/dsnet/compress v0.0.1 // indirect
-	github.com/emirpasic/gods v1.12.0 // indirect
+	github.com/emirpasic/gods v1.18.1 // indirect
+	github.com/go-asn1-ber/asn1-ber v1.5.4 // indirect
 	github.com/go-git/gcfg v1.5.0 // indirect
-	github.com/go-git/go-billy/v5 v5.3.1 // indirect
+	github.com/go-git/go-billy/v5 v5.4.0 // indirect
 	github.com/go-ole/go-ole v1.2.6 // indirect
 	github.com/golang-jwt/jwt/v4 v4.4.1 // indirect
 	github.com/golang-sql/civil v0.0.0-20190719163853-cb61b32ac6fe // indirect
@@ -96,44 +102,51 @@ require (
 	github.com/google/go-github/v45 v45.2.0 // indirect
 	github.com/google/go-querystring v1.1.0 // indirect
 	github.com/google/pprof v0.0.0-20211214055906-6f57359322fd // indirect
-	github.com/googleapis/enterprise-certificate-proxy v0.1.0 // indirect
-	github.com/googleapis/gax-go/v2 v2.5.1 // indirect
+	github.com/googleapis/enterprise-certificate-proxy v0.2.0 // indirect
+	github.com/googleapis/gax-go/v2 v2.7.0 // indirect
 	github.com/h2non/parth v0.0.0-20190131123155-b4df798d6542 // indirect
+	github.com/hashicorp/errwrap v1.0.0 // indirect
 	github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
-	github.com/imdario/mergo v0.3.12 // indirect
+	github.com/hashicorp/go-multierror v1.1.1 // indirect
+	github.com/imdario/mergo v0.3.13 // indirect
 	github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
 	github.com/jmespath/go-jmespath v0.4.0 // indirect
 	github.com/jpillora/s3 v1.1.4 // indirect
-	github.com/kevinburke/ssh_config v0.0.0-20201106050909-4977a11b4351 // indirect
-	github.com/klauspost/compress v1.15.5 // indirect
+	github.com/kevinburke/ssh_config v1.2.0 // indirect
+	github.com/klauspost/compress v1.15.11 // indirect
 	github.com/klauspost/pgzip v1.2.5 // indirect
 	github.com/mattn/go-isatty v0.0.16 // indirect
 	github.com/mitchellh/go-homedir v1.1.0 // indirect
 	github.com/montanaflynn/stats v0.0.0-20171201202039-1bf9dbcd8cbe // indirect
 	github.com/nwaples/rardecode/v2 v2.0.0-beta.2 // indirect
+	github.com/onsi/ginkgo v1.16.5 // indirect
+	github.com/onsi/gomega v1.23.0 // indirect
 	github.com/pierrec/lz4/v4 v4.1.14 // indirect
+	github.com/pjbgf/sha1cd v0.2.3 // indirect
 	github.com/pkg/diff v0.0.0-20200914180035-5b29258ca4f7 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/skeema/knownhosts v1.1.0 // indirect
 	github.com/therootcompany/xz v1.0.1 // indirect
 	github.com/ulikunitz/xz v0.5.10 // indirect
-	github.com/xanzy/ssh-agent v0.3.0 // indirect
+	github.com/xanzy/ssh-agent v0.3.3 // indirect
 	github.com/xdg-go/pbkdf2 v1.0.0 // indirect
 	github.com/xdg-go/scram v1.1.1 // indirect
 	github.com/xdg-go/stringprep v1.0.3 // indirect
 	github.com/youmark/pkcs8 v0.0.0-20181117223130-1be2e3e5546d // indirect
 	github.com/yusufpapurcu/wmi v1.2.2 // indirect
-	go.opencensus.io v0.23.0 // indirect
+	go.opencensus.io v0.24.0 // indirect
 	go.uber.org/atomic v1.7.0 // indirect
 	go.uber.org/multierr v1.6.0 // indirect
-	golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4 // indirect
-	golang.org/x/net v0.0.0-20220909164309-bea034e7d591 // indirect
-	golang.org/x/sys v0.0.0-20220908150016-7ac13a9a928d // indirect
-	golang.org/x/text v0.3.7 // indirect
-	golang.org/x/time v0.0.0-20220722155302-e5dcc9cfc0b9 // indirect
-	golang.org/x/tools v0.1.12 // indirect
-	google.golang.org/api v0.96.0 // indirect
+	golang.org/x/mod v0.7.0 // indirect
+	golang.org/x/net v0.5.0 // indirect
+	golang.org/x/sys v0.4.0 // indirect
+	golang.org/x/text v0.6.0 // indirect
+	golang.org/x/time v0.0.0-20220922220347-f3bd1da661af // indirect
+	golang.org/x/tools v0.3.0 // indirect
+	google.golang.org/api v0.103.0 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
-	google.golang.org/grpc v1.49.0 // indirect
+	google.golang.org/grpc v1.51.0 // indirect
 	gopkg.in/warnings.v0 v0.1.2 // indirect
+	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )
@@ -49,8 +49,12 @@ If you think that something should be included outside of these guidelines, plea
   ```bash
   go run hack/generate/generate.go detector <DetectorType enum name>
   ```
+3. Add Secret Scanner

-3. Complete the secret detector.
+   Add the secret scanner to the `pkg/engine/defaults.go` file like `github.com/trufflesecurity/trufflehog/v3/pkg/detectors/<detector_name>` and 
+   `<detector_name>.Scanner{},`
+
+4. Complete the secret detector.

   The previous step templated a boilerplate + some example code as a package in the `pkg/detectors` folder for you to work on.
   The secret detector can be completed with these general steps:
@@ -104,4 +108,4 @@ Now, the detector test should attempt to load the given env key from that file.
 ### Testing a detector
 ```bash
   go test ./pkg/detectors/<detector> -tags=detectors
-   ```
+   ```
@@ -156,15 +156,13 @@ func main() {
 		}

 		for _, repo := range strings.Split(*scanCmdRepo, ",") {
-			if err := sem.Acquire(ctx, 1); err != nil {
-				log.Fatal(err)
-			}
+			sem.Acquire(ctx, 1)
 			wgChunkers.Add(1)
 			go func(r string) {
 				defer sem.Release(1)
 				defer wgChunkers.Done()
 				log.Infof("cloning %s", r)
-				path, repo, err := git.CloneRepoUsingUnauthenticated(r)
+				path, repo, err := git.CloneRepoUsingUnauthenticated(ctx, r)
 				if err != nil {
 					log.Fatal(err)
 				}
@@ -2,7 +2,6 @@ package main

 import (
 	"fmt"
-	"log"
 	"net/http"
 	_ "net/http/pprof"
 	"os"
@@ -19,9 +18,11 @@ import (
 	"gopkg.in/alecthomas/kingpin.v2"

 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/config"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/context"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/decoders"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/engine"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/log"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/output"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/sources"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/sources/git"
@@ -30,15 +31,17 @@ import (
 )

 var (
-	cli            = kingpin.New("TruffleHog", "TruffleHog is a tool for finding credentials.")
-	cmd            string
-	debug          = cli.Flag("debug", "Run in debug mode.").Bool()
-	trace          = cli.Flag("trace", "Run in trace mode.").Bool()
-	jsonOut        = cli.Flag("json", "Output in JSON format.").Short('j').Bool()
-	jsonLegacy     = cli.Flag("json-legacy", "Use the pre-v3.0 JSON format. Only works with git, gitlab, and github sources.").Bool()
-	concurrency    = cli.Flag("concurrency", "Number of concurrent workers.").Default(strconv.Itoa(runtime.NumCPU())).Int()
-	noVerification = cli.Flag("no-verification", "Don't verify the results.").Bool()
-	onlyVerified   = cli.Flag("only-verified", "Only output verified results.").Bool()
+	cli              = kingpin.New("TruffleHog", "TruffleHog is a tool for finding credentials.")
+	cmd              string
+	debug            = cli.Flag("debug", "Run in debug mode.").Bool()
+	trace            = cli.Flag("trace", "Run in trace mode.").Bool()
+	jsonOut          = cli.Flag("json", "Output in JSON format.").Short('j').Bool()
+	jsonLegacy       = cli.Flag("json-legacy", "Use the pre-v3.0 JSON format. Only works with git, gitlab, and github sources.").Bool()
+	concurrency      = cli.Flag("concurrency", "Number of concurrent workers.").Default(strconv.Itoa(runtime.NumCPU())).Int()
+	noVerification   = cli.Flag("no-verification", "Don't verify the results.").Bool()
+	onlyVerified     = cli.Flag("only-verified", "Only output verified results.").Bool()
+	filterUnverified = cli.Flag("filter-unverified", "Only output first unverified result per chunk per detector if there are more than one results.").Bool()
+	configFilename   = cli.Flag("config", "Path to configuration file.").ExistingFile()
 	// rules = cli.Flag("rules", "Path to file with custom rules.").String()
 	printAvgDetectorTime = cli.Flag("print-avg-detector-time", "Print the average time spent on each detector.").Bool()
 	noUpdate             = cli.Flag("no-update", "Don't check for updates.").Bool()
@@ -62,12 +65,16 @@ var (
 	githubScanToken      = githubScan.Flag("token", "GitHub token. Can be provided with environment variable GITHUB_TOKEN.").Envar("GITHUB_TOKEN").String()
 	githubIncludeForks   = githubScan.Flag("include-forks", "Include forks in scan.").Bool()
 	githubIncludeMembers = githubScan.Flag("include-members", "Include organization member repositories in scan.").Bool()
+	githubIncludeRepos   = githubScan.Flag("include-repos", `Repositories to include in an org scan. This can also be a glob pattern. You can repeat this flag. Must use Github repo full name. Example: "trufflesecurity/trufflehog", "trufflesecurity/t*"`).Strings()
+	githubExcludeRepos   = githubScan.Flag("exclude-repos", `Repositories to exclude in an org scan. This can also be a glob pattern. You can repeat this flag. Must use Github repo full name. Example: "trufflesecurity/driftwood", "trufflesecurity/d*"`).Strings()

 	gitlabScan = cli.Command("gitlab", "Find credentials in GitLab repositories.")
 	// TODO: Add more GitLab options
-	gitlabScanEndpoint = gitlabScan.Flag("endpoint", "GitLab endpoint.").Default("https://gitlab.com").String()
-	gitlabScanRepos    = gitlabScan.Flag("repo", "GitLab repo url. You can repeat this flag. Leave empty to scan all repos accessible with provided credential. Example: https://gitlab.com/org/repo.git").Strings()
-	gitlabScanToken    = gitlabScan.Flag("token", "GitLab token. Can be provided with environment variable GITLAB_TOKEN.").Envar("GITLAB_TOKEN").Required().String()
+	gitlabScanEndpoint     = gitlabScan.Flag("endpoint", "GitLab endpoint.").Default("https://gitlab.com").String()
+	gitlabScanRepos        = gitlabScan.Flag("repo", "GitLab repo url. You can repeat this flag. Leave empty to scan all repos accessible with provided credential. Example: https://gitlab.com/org/repo.git").Strings()
+	gitlabScanToken        = gitlabScan.Flag("token", "GitLab token. Can be provided with environment variable GITLAB_TOKEN.").Envar("GITLAB_TOKEN").Required().String()
+	gitlabScanIncludePaths = gitlabScan.Flag("include-paths", "Path to file with newline separated regexes for files to include in scan.").Short('i').String()
+	gitlabScanExcludePaths = gitlabScan.Flag("exclude-paths", "Path to file with newline separated regexes for files to exclude in scan.").Short('x').String()

 	filesystemScan        = cli.Command("filesystem", "Find credentials in a filesystem.")
 	filesystemDirectories = filesystemScan.Flag("directory", "Path to directory to scan. You can repeat this flag.").Required().Strings()
@@ -88,6 +95,9 @@ var (
 	syslogTLSCert  = syslogScan.Flag("cert", "Path to TLS cert.").String()
 	syslogTLSKey   = syslogScan.Flag("key", "Path to TLS key.").String()
 	syslogFormat   = syslogScan.Flag("format", "Log format. Can be rfc3164 or rfc5424").String()
+
+	circleCiScan      = cli.Command("circleci", "Scan CircleCI")
+	circleCiScanToken = circleCiScan.Flag("token", "CircleCI token. Can also be provided with environment variable").Envar("CIRCLECI_TOKEN").Required().String()
 )

 func init() {
@@ -107,9 +117,11 @@ func init() {
 	}
 	switch {
 	case *trace:
+		log.SetLevel(5)
 		logrus.SetLevel(logrus.TraceLevel)
 		logrus.Debugf("running version %s", version.BuildVersion)
 	case *debug:
+		log.SetLevel(2)
 		logrus.SetLevel(logrus.DebugLevel)
 		logrus.Debugf("running version %s", version.BuildVersion)
 	default:
@@ -141,7 +153,7 @@ func main() {

 func run(state overseer.State) {
 	if *debug {
-		fmt.Println("trufflehog " + version.BuildVersion)
+		logrus.Debugf("trufflehog %s", version.BuildVersion)
 	}

 	if *githubScanToken != "" {
@@ -166,12 +178,27 @@ func run(state overseer.State) {
 			}
 		}()
 	}
+	logger, sync := log.New("trufflehog", log.WithConsoleSink(os.Stderr))
+	context.SetDefaultLogger(logger)
+	defer func() { _ = sync() }()
+
+	conf := &config.Config{}
+	if *configFilename != "" {
+		var err error
+		conf, err = config.Read(*configFilename)
+		if err != nil {
+			logger.Error(err, "error parsing the provided configuration file")
+			os.Exit(1)
+		}
+	}

 	ctx := context.TODO()
 	e := engine.Start(ctx,
 		engine.WithConcurrency(*concurrency),
 		engine.WithDecoders(decoders.DefaultDecoders()...),
 		engine.WithDetectors(!*noVerification, engine.DefaultDetectors()...),
+		engine.WithDetectors(!*noVerification, conf.Detectors...),
+		engine.WithFilterUnverified(*filterUnverified),
 	)

 	filter, err := common.FilterFromFiles(*gitScanIncludePaths, *gitScanExcludePaths)
@@ -183,7 +210,7 @@ func run(state overseer.State) {
 	var remote bool
 	switch cmd {
 	case gitScan.FullCommand():
-		repoPath, remote, err = git.PrepareRepoSinceCommit(*gitScanURI, *gitScanSinceCommit)
+		repoPath, remote, err = git.PrepareRepoSinceCommit(ctx, *gitScanURI, *gitScanSinceCommit)
 		if err != nil || repoPath == "" {
 			logrus.WithError(err).Fatal("error preparing git repo for scanning")
 		}
@@ -204,7 +231,7 @@ func run(state overseer.State) {
 		}
 	case githubScan.FullCommand():
 		if len(*githubScanOrgs) == 0 && len(*githubScanRepos) == 0 {
-			log.Fatal("You must specify at least one organization or repository.")
+			logrus.Fatal("You must specify at least one organization or repository.")
 		}

 		github := func(c *sources.Config) {
@@ -215,16 +242,24 @@ func run(state overseer.State) {
 			c.IncludeForks = *githubIncludeForks
 			c.IncludeMembers = *githubIncludeMembers
 			c.Concurrency = *concurrency
+			c.ExcludeRepos = *githubExcludeRepos
+			c.IncludeRepos = *githubIncludeRepos
 		}

 		if err = e.ScanGitHub(ctx, sources.NewConfig(github)); err != nil {
 			logrus.WithError(err).Fatal("Failed to scan Github.")
 		}
 	case gitlabScan.FullCommand():
+		filter, err := common.FilterFromFiles(*gitlabScanIncludePaths, *gitlabScanExcludePaths)
+		if err != nil {
+			logrus.WithError(err).Fatal("could not create filter")
+		}
+
 		gitlab := func(c *sources.Config) {
 			c.Endpoint = *gitlabScanEndpoint
 			c.Token = *gitlabScanToken
 			c.Repos = *gitlabScanRepos
+			c.Filter = filter
 		}

 		if err = e.ScanGitLab(ctx, sources.NewConfig(gitlab)); err != nil {
@@ -261,6 +296,10 @@ func run(state overseer.State) {
 		if err = e.ScanSyslog(ctx, sources.NewConfig(syslog)); err != nil {
 			logrus.WithError(err).Fatal("Failed to scan syslog.")
 		}
+	case circleCiScan.FullCommand():
+		if err = e.ScanCircleCI(ctx, *circleCiScanToken); err != nil {
+			logrus.WithError(err).Fatal("Failed to scan CircleCI.")
+		}
 	}
 	// asynchronously wait for scanning to finish and cleanup
 	go e.Finish(ctx)
@@ -280,7 +319,7 @@ func run(state overseer.State) {

 		switch {
 		case *jsonLegacy:
-			output.PrintLegacyJSON(&r)
+			output.PrintLegacyJSON(ctx, &r)
 		case *jsonOut:
 			output.PrintJSON(&r)
 		default:
@@ -288,6 +327,7 @@ func run(state overseer.State) {
 		}
 	}
 	logrus.Debugf("scanned %d chunks", e.ChunksScanned())
+	logrus.Debugf("scanned %d bytes", e.BytesScanned())

 	if *printAvgDetectorTime {
 		printAverageDetectorTime(e)
@@ -1,36 +0,0 @@
-package common
-
-import (
-	"bufio"
-	"errors"
-	"io"
-
-	log "github.com/sirupsen/logrus"
-)
-
-const (
-	ChunkSize = 10 * 1024
-	PeekSize  = 3 * 1024
-)
-
-func ChunkReader(r io.Reader) chan []byte {
-	chunkChan := make(chan []byte)
-	go func() {
-		defer close(chunkChan)
-		reader := bufio.NewReaderSize(bufio.NewReader(r), ChunkSize)
-		for {
-			chunk := make([]byte, ChunkSize)
-			n, err := reader.Read(chunk)
-			if err != nil && !errors.Is(err, io.EOF) {
-				log.WithError(err).Error("Error chunking reader.")
-				break
-			}
-			peekData, _ := reader.Peek(PeekSize)
-			chunkChan <- append(chunk[:n], peekData...)
-			if errors.Is(err, io.EOF) {
-				break
-			}
-		}
-	}()
-	return chunkChan
-}
@@ -9,6 +9,7 @@ import (
 	"time"

 	"github.com/hashicorp/go-retryablehttp"
+	"github.com/sirupsen/logrus"
 )

 var caCerts = []string{
@@ -93,7 +94,7 @@ func NewCustomTransport(T http.RoundTripper) *CustomTransport {

 func PinnedRetryableHttpClient() *http.Client {
 	httpClient := retryablehttp.NewClient()
-	httpClient.Logger = nil
+	httpClient.Logger = logrus.WithField("name", "PinnedRetryableHttpClient").WithField("level", logrus.DebugLevel)
 	httpClient.HTTPClient.Transport = NewCustomTransport(&http.Transport{
 		TLSClientConfig: &tls.Config{
 			RootCAs: PinnedCertPool(),
@@ -115,7 +116,7 @@ func PinnedRetryableHttpClient() *http.Client {
 func RetryableHttpClient() *http.Client {
 	httpClient := retryablehttp.NewClient()
 	httpClient.RetryMax = 3
-	httpClient.Logger = nil
+	httpClient.Logger = logrus.WithField("name", "RetryableHttpClient").WithField("level", logrus.DebugLevel)
 	httpClient.HTTPClient.Timeout = 3 * time.Second
 	httpClient.HTTPClient.Transport = NewCustomTransport(nil)
 	return httpClient.StandardClient()
@@ -124,7 +125,7 @@ func RetryableHttpClient() *http.Client {
 func RetryableHttpClientTimeout(timeOutSeconds int64) *http.Client {
 	httpClient := retryablehttp.NewClient()
 	httpClient.RetryMax = 3
-	httpClient.Logger = nil
+	httpClient.Logger = logrus.WithField("name", "RetryableHttpClientTimeout").WithField("level", logrus.DebugLevel)
 	httpClient.HTTPClient.Timeout = time.Duration(timeOutSeconds) * time.Second
 	httpClient.HTTPClient.Transport = NewCustomTransport(nil)
 	return httpClient.StandardClient()
@@ -18,7 +18,10 @@ func Recover(ctx context.Context) {
 		if eventID := sentry.CurrentHub().Recover(err); eventID != nil {
 			ctx.Logger().Info("panic captured", "event_id", *eventID)
 		}
-		fmt.Fprint(os.Stderr, panicStack)
+		ctx.Logger().Error(fmt.Errorf("panic"), "recovered from panic",
+			"stack-trace", panicStack,
+			"recover", err,
+		)
 		if !sentry.Flush(time.Second * 5) {
 			ctx.Logger().Info("sentry flush failed")
 		}
@@ -32,7 +35,10 @@ func RecoverWithExit(ctx context.Context) {
 		if eventID := sentry.CurrentHub().Recover(err); eventID != nil {
 			ctx.Logger().Info("panic captured", "event_id", *eventID)
 		}
-		fmt.Fprint(os.Stderr, panicStack)
+		ctx.Logger().Error(fmt.Errorf("panic"), "recovered from panic before exiting",
+			"stack-trace", panicStack,
+			"recover", err,
+		)
 		if !sentry.Flush(time.Second * 5) {
 			ctx.Logger().Info("sentry flush failed")
 		}
@@ -2,22 +2,14 @@ package common

 import (
 	"path/filepath"
-
-	"github.com/h2non/filetype"
 )

 var (
 	KB, MB, GB, TB, PB = 1e3, 1e6, 1e9, 1e12, 1e15
-	IGNORED_EXTENSIONS = []string{"pdf", "mp4", "avi", "mpeg", "mpg", "mov", "wmv", "m4p", "swf", "mp2", "flv", "vob", "webm", "hdv", "3gp", "ogg", "mp3", "wav", "flac", "tif", "tiff", "jpg", "jpeg", "png", "gif", "zip", "webp"}
+	IGNORED_EXTENSIONS = []string{"mp4", "avi", "mpeg", "mpg", "mov", "wmv", "m4p", "swf", "mp2", "flv", "vob", "webm", "hdv", "3gp", "ogg", "mp3", "wav", "flac", "webp"}
 )

-func SkipFile(filename string, data []byte) bool {
-	if filepath.Ext(filename) == "" {
-		//no sepcified extension, check mimetype
-		if filetype.IsArchive(data[:256]) {
-			return true
-		}
-	}
+func SkipFile(filename string) bool {
 	for _, ext := range IGNORED_EXTENSIONS {
 		if filepath.Ext(filename) == ext {
 			return true
@@ -0,0 +1,45 @@
+package config
+
+import (
+	"os"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/custom_detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/custom_detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/protoyaml"
+)
+
+// Config holds user supplied configuration.
+type Config struct {
+	Detectors []detectors.Detector
+}
+
+// Read parses a given filename into a Config.
+func Read(filename string) (*Config, error) {
+	input, err := os.ReadFile(filename)
+	if err != nil {
+		return nil, err
+	}
+	return NewYAML(input)
+}
+
+// NewYAML parses the given YAML data into a Config.
+func NewYAML(input []byte) (*Config, error) {
+	// Parse the raw YAML into a structure.
+	var messages custom_detectorspb.CustomDetectors
+	if err := protoyaml.UnmarshalStrict(input, &messages); err != nil {
+		return nil, err
+	}
+	// Convert the structured YAML into detectors.
+	var detectors []detectors.Detector
+	for _, detectorConfig := range messages.Detectors {
+		detector, err := custom_detectors.NewWebhookCustomRegex(detectorConfig)
+		if err != nil {
+			return nil, err
+		}
+		detectors = append(detectors, detector)
+	}
+	return &Config{
+		Detectors: detectors,
+	}, nil
+}
@@ -2,6 +2,8 @@ package context

 import (
 	"context"
+	"fmt"
+	"runtime/debug"
 	"time"

 	"github.com/go-logr/logr"
@@ -38,6 +40,7 @@ type logCtx struct {
 	// Embed context.Context to get all methods for free.
 	context.Context
 	log logr.Logger
+	err *error
 }

 // Logger returns a structured logger.
@@ -45,6 +48,13 @@ func (l logCtx) Logger() logr.Logger {
 	return l.log
 }

+func (l logCtx) Err() error {
+	if l.err != nil && *l.err != nil {
+		return *l.err
+	}
+	return l.Context.Err()
+}
+
 // Background returns context.Background with a default logger.
 func Background() Context {
 	return logCtx{
@@ -64,30 +74,33 @@ func TODO() Context {
 // WithCancel returns context.WithCancel with the log object propagated.
 func WithCancel(parent Context) (Context, context.CancelFunc) {
 	ctx, cancel := context.WithCancel(parent)
-	return logCtx{
+	lCtx := logCtx{
 		log:     parent.Logger(),
 		Context: ctx,
-	}, cancel
+	}
+	return captureCancelCallstack(lCtx, cancel)
 }

 // WithDeadline returns context.WithDeadline with the log object propagated and
 // the deadline added to the structured log values.
 func WithDeadline(parent Context, d time.Time) (Context, context.CancelFunc) {
 	ctx, cancel := context.WithDeadline(parent, d)
-	return logCtx{
+	lCtx := logCtx{
 		log:     parent.Logger().WithValues("deadline", d),
 		Context: ctx,
-	}, cancel
+	}
+	return captureCancelCallstack(lCtx, cancel)
 }

 // WithTimeout returns context.WithTimeout with the log object propagated and
 // the timeout added to the structured log values.
 func WithTimeout(parent Context, timeout time.Duration) (Context, context.CancelFunc) {
 	ctx, cancel := context.WithTimeout(parent, timeout)
-	return logCtx{
+	lCtx := logCtx{
 		log:     parent.Logger().WithValues("timeout", timeout),
 		Context: ctx,
-	}, cancel
+	}
+	return captureCancelCallstack(lCtx, cancel)
 }

 // WithValue returns context.WithValue with the log object propagated and
@@ -136,3 +149,23 @@ func AddLogger(parent context.Context) Context {
 func SetDefaultLogger(l logr.Logger) {
 	defaultLogger = l
 }
+
+// captureCancelCallstack is a helper function to capture the callstack where
+// the cancel function was first called.
+func captureCancelCallstack(ctx logCtx, f context.CancelFunc) (Context, context.CancelFunc) {
+	if ctx.err == nil {
+		var err error
+		ctx.err = &err
+	}
+	return ctx, func() {
+		// We must check Err() before calling f() since f() sets the error.
+		// If there's already an error, do nothing special.
+		if ctx.Err() != nil {
+			f()
+			return
+		}
+		f()
+		// Set the error with the stacktrace if the err pointer is non-nil.
+		*ctx.err = fmt.Errorf("%w (%s)", ctx.Err(), string(debug.Stack()))
+	}
+}
@@ -169,3 +169,46 @@ func TestDiscardLogger(t *testing.T) {
 	ctx := Background()
 	ctx.Logger().Info("this shouldn't panic")
 }
+
+func TestErrCallstack(t *testing.T) {
+	c, cancel := WithCancel(Background())
+	ctx := c.(logCtx)
+	cancel()
+	select {
+	case <-ctx.Done():
+		assert.Contains(t, ctx.Err().Error(), "TestErrCallstack")
+	case <-time.After(1 * time.Second):
+		assert.Fail(t, "context should be done")
+	}
+}
+
+func TestErrCallstackTimeout(t *testing.T) {
+	ctx, cancel := WithTimeout(Background(), 10*time.Millisecond)
+	defer cancel()
+
+	select {
+	case <-ctx.Done():
+		// Deadline exceeded errors will not have a callstack from the cancel
+		// function.
+		assert.NotContains(t, ctx.Err().Error(), "TestErrCallstackTimeout")
+	case <-time.After(1 * time.Second):
+		assert.Fail(t, "context should be done")
+	}
+}
+
+func TestErrCallstackTimeoutCancel(t *testing.T) {
+	ctx, cancel := WithTimeout(Background(), 10*time.Millisecond)
+
+	var err error
+	select {
+	case <-ctx.Done():
+		err = ctx.Err()
+	case <-time.After(1 * time.Second):
+		assert.Fail(t, "context should be done")
+	}
+
+	// Calling cancel after deadline exceeded should not overwrite the original
+	// error.
+	cancel()
+	assert.Equal(t, err, ctx.Err())
+}
@@ -0,0 +1,226 @@
+package custom_detectors
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"net/http"
+	"regexp"
+	"strings"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/custom_detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+// The maximum number of matches from one chunk. This const is used when
+// permutating each regex match to protect the scanner from doing too much work
+// for poorly defined regexps.
+const maxTotalMatches = 100
+
+// customRegexWebhook is a CustomRegex with webhook validation that is
+// guaranteed to be valid (assuming the data is not changed after
+// initialization).
+type customRegexWebhook struct {
+	*custom_detectorspb.CustomRegex
+}
+
+// Ensure the Scanner satisfies the interface at compile time.
+var _ detectors.Detector = (*customRegexWebhook)(nil)
+
+// NewWebhookCustomRegex initializes and validates a customRegexWebhook. An
+// unexported type is intentionally returned here to ensure the values have
+// been validated.
+func NewWebhookCustomRegex(pb *custom_detectorspb.CustomRegex) (*customRegexWebhook, error) {
+	// TODO: Return all validation errors.
+	if err := ValidateKeywords(pb.Keywords); err != nil {
+		return nil, err
+	}
+	if err := ValidateRegex(pb.Regex); err != nil {
+		return nil, err
+	}
+
+	for _, verify := range pb.Verify {
+		if err := ValidateVerifyEndpoint(verify.Endpoint, verify.Unsafe); err != nil {
+			return nil, err
+		}
+		if err := ValidateVerifyHeaders(verify.Headers); err != nil {
+			return nil, err
+		}
+	}
+
+	// TODO: Copy only necessary data out of pb.
+	return &customRegexWebhook{pb}, nil
+}
+
+var httpClient = common.SaneHttpClient()
+
+func (c *customRegexWebhook) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
+	dataStr := string(data)
+	regexMatches := make(map[string][][]string, len(c.GetRegex()))
+
+	// Find all submatches for each regex.
+	for name, regex := range c.GetRegex() {
+		regex, err := regexp.Compile(regex)
+		if err != nil {
+			// This will only happen if the regex is invalid.
+			return nil, err
+		}
+		regexMatches[name] = regex.FindAllStringSubmatch(dataStr, -1)
+	}
+
+	// Permutate each individual match.
+	// {
+	//    "foo": [["match1"]]
+	//    "bar": [["match2"], ["match3"]]
+	// }
+	// becomes
+	// [
+	//    {"foo": ["match1"], "bar": ["match2"]},
+	//    {"foo": ["match1"], "bar": ["match3"]},
+	// ]
+	matches := permutateMatches(regexMatches)
+
+	// Create result object and test for verification.
+	for _, match := range matches {
+		if common.IsDone(ctx) {
+			// TODO: Log we're possibly leaving out results.
+			return results, nil
+		}
+		var raw string
+		for _, values := range match {
+			// values[0] contains the entire regex match.
+			raw += values[0]
+		}
+		result := detectors.Result{
+			DetectorType: detectorspb.DetectorType_CustomRegex,
+			Raw:          []byte(raw),
+		}
+
+		if isKnownFalsePositive(match) {
+			continue
+		}
+		if !verify {
+			results = append(results, result)
+			continue
+		}
+		// Verify via webhook.
+		jsonBody, err := json.Marshal(map[string]map[string][]string{
+			c.GetName(): match,
+		})
+		if err != nil {
+			continue
+		}
+		// Try each config until we successfully verify.
+		for _, verifyConfig := range c.GetVerify() {
+			if common.IsDone(ctx) {
+				// TODO: Log we're possibly leaving out results.
+				return results, nil
+			}
+			req, err := http.NewRequestWithContext(ctx, "POST", verifyConfig.GetEndpoint(), bytes.NewReader(jsonBody))
+			if err != nil {
+				continue
+			}
+			for _, header := range verifyConfig.GetHeaders() {
+				key, value, found := strings.Cut(header, ":")
+				if !found {
+					// Should be unreachable due to validation.
+					continue
+				}
+				req.Header.Add(key, strings.TrimLeft(value, "\t\n\v\f\r "))
+			}
+			res, err := httpClient.Do(req)
+			if err != nil {
+				continue
+			}
+			// TODO: Read response body.
+			res.Body.Close()
+			if res.StatusCode == http.StatusOK {
+				result.Verified = true
+				break
+			}
+		}
+		results = append(results, result)
+	}
+
+	return results, nil
+}
+
+func (c *customRegexWebhook) Keywords() []string {
+	return c.GetKeywords()
+}
+
+// productIndices produces a permutation of indices for each length. Example:
+// productIndices(3, 2) -> [[0 0] [1 0] [2 0] [0 1] [1 1] [2 1]]. It returns
+// a slice of length no larger than maxTotalMatches.
+func productIndices(lengths ...int) [][]int {
+	count := 1
+	for _, l := range lengths {
+		count *= l
+	}
+	if count == 0 {
+		return nil
+	}
+	if count > maxTotalMatches {
+		count = maxTotalMatches
+	}
+
+	results := make([][]int, count)
+	for i := 0; i < count; i++ {
+		j := 1
+		result := make([]int, 0, len(lengths))
+		for _, l := range lengths {
+			result = append(result, (i/j)%l)
+			j *= l
+		}
+		results[i] = result
+	}
+	return results
+}
+
+// permutateMatches converts the list of all regex matches into all possible
+// permutations selecting one from each named entry in the map. For example:
+// {"foo": [matchA, matchB], "bar": [matchC]} becomes
+//
+// [{"foo": matchA, "bar": matchC}, {"foo": matchB, "bar": matchC}]
+func permutateMatches(regexMatches map[string][][]string) []map[string][]string {
+	// Get a consistent order for names and their matching lengths.
+	// The lengths are used in calculating the permutation so order matters.
+	names := make([]string, 0, len(regexMatches))
+	lengths := make([]int, 0, len(regexMatches))
+	for key, value := range regexMatches {
+		names = append(names, key)
+		lengths = append(lengths, len(value))
+	}
+
+	// Permutate all the indices for each match. For example, if "foo" has
+	// [matchA, matchB] and "bar" has [matchC], we will get indices [0 0] [1 0].
+	permutationIndices := productIndices(lengths...)
+
+	// Build {"foo": matchA, "bar": matchC} and {"foo": matchB, "bar": matchC}
+	// from the indices.
+	var matches []map[string][]string
+	for _, permutation := range permutationIndices {
+		candidate := make(map[string][]string, len(permutationIndices))
+		for i, name := range names {
+			candidate[name] = regexMatches[name][permutation[i]]
+		}
+		matches = append(matches, candidate)
+	}
+
+	return matches
+}
+
+// This function will check false positives for common test words, but also it
+// will make sure the key appears 'random' enough to be a real key.
+func isKnownFalsePositive(match map[string][]string) bool {
+	for _, values := range match {
+		for _, value := range values {
+			if detectors.IsKnownFalsePositive(value, detectors.DefaultFalsePositives, true) {
+				return true
+			}
+		}
+	}
+	return false
+}
@@ -0,0 +1,200 @@
+package custom_detectors
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/custom_detectorspb"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/protoyaml"
+)
+
+func TestCustomRegexTemplateParsing(t *testing.T) {
+	testCustomRegexTemplateYaml := `name: Internal bi tool
+keywords:
+- secret_v1_
+- pat_v2_
+regex:
+  id_pat_example: ([a-zA-Z0-9]{32})
+  secret_pat_example: ([a-zA-Z0-9]{32})
+verify:
+- endpoint: http://localhost:8000/{id_pat_example}
+  unsafe: true
+  headers:
+  - 'Authorization: Bearer {secret_pat_example.0}'
+  successRanges:
+  - 200-250
+  - '288'`
+
+	var got custom_detectorspb.CustomRegex
+	assert.NoError(t, protoyaml.UnmarshalStrict([]byte(testCustomRegexTemplateYaml), &got))
+	assert.Equal(t, "Internal bi tool", got.Name)
+	assert.Equal(t, []string{"secret_v1_", "pat_v2_"}, got.Keywords)
+	assert.Equal(t, map[string]string{
+		"id_pat_example":     "([a-zA-Z0-9]{32})",
+		"secret_pat_example": "([a-zA-Z0-9]{32})",
+	}, got.Regex)
+	assert.Equal(t, 1, len(got.Verify))
+	assert.Equal(t, "http://localhost:8000/{id_pat_example}", got.Verify[0].Endpoint)
+	assert.Equal(t, true, got.Verify[0].Unsafe)
+	assert.Equal(t, []string{"Authorization: Bearer {secret_pat_example.0}"}, got.Verify[0].Headers)
+	assert.Equal(t, []string{"200-250", "288"}, got.Verify[0].SuccessRanges)
+}
+
+func TestCustomRegexWebhookParsing(t *testing.T) {
+	testCustomRegexWebhookYaml := `name: Internal bi tool
+keywords:
+- secret_v1_
+- pat_v2_
+regex:
+  id_pat_example: ([a-zA-Z0-9]{32})
+  secret_pat_example: ([a-zA-Z0-9]{32})
+verify:
+- endpoint: http://localhost:8000/
+  unsafe: true
+  headers:
+  - 'Authorization: Bearer token'`
+
+	var got custom_detectorspb.CustomRegex
+	assert.NoError(t, protoyaml.UnmarshalStrict([]byte(testCustomRegexWebhookYaml), &got))
+	assert.Equal(t, "Internal bi tool", got.Name)
+	assert.Equal(t, []string{"secret_v1_", "pat_v2_"}, got.Keywords)
+	assert.Equal(t, map[string]string{
+		"id_pat_example":     "([a-zA-Z0-9]{32})",
+		"secret_pat_example": "([a-zA-Z0-9]{32})",
+	}, got.Regex)
+	assert.Equal(t, 1, len(got.Verify))
+	assert.Equal(t, "http://localhost:8000/", got.Verify[0].Endpoint)
+	assert.Equal(t, true, got.Verify[0].Unsafe)
+	assert.Equal(t, []string{"Authorization: Bearer token"}, got.Verify[0].Headers)
+}
+
+// TestCustomDetectorsParsing tests the full `detectors` configuration.
+func TestCustomDetectorsParsing(t *testing.T) {
+	// TODO: Support both template and webhook.
+	testYamlConfig := `detectors:
+- name: Internal bi tool
+  keywords:
+  - secret_v1_
+  - pat_v2_
+  regex:
+    id_pat_example: ([a-zA-Z0-9]{32})
+    secret_pat_example: ([a-zA-Z0-9]{32})
+  verify:
+  - endpoint: http://localhost:8000/
+    unsafe: true
+    headers:
+    - 'Authorization: Bearer token'`
+
+	var messages custom_detectorspb.CustomDetectors
+	assert.NoError(t, protoyaml.UnmarshalStrict([]byte(testYamlConfig), &messages))
+	assert.Equal(t, 1, len(messages.Detectors))
+
+	got := messages.Detectors[0]
+	assert.Equal(t, "Internal bi tool", got.Name)
+	assert.Equal(t, []string{"secret_v1_", "pat_v2_"}, got.Keywords)
+	assert.Equal(t, map[string]string{
+		"id_pat_example":     "([a-zA-Z0-9]{32})",
+		"secret_pat_example": "([a-zA-Z0-9]{32})",
+	}, got.Regex)
+	assert.Equal(t, 1, len(got.Verify))
+	assert.Equal(t, "http://localhost:8000/", got.Verify[0].Endpoint)
+	assert.Equal(t, true, got.Verify[0].Unsafe)
+	assert.Equal(t, []string{"Authorization: Bearer token"}, got.Verify[0].Headers)
+}
+
+func TestFromData_InvalidRegEx(t *testing.T) {
+	c := &customRegexWebhook{
+		&custom_detectorspb.CustomRegex{
+			Name:     "Internal bi tool",
+			Keywords: []string{"secret_v1_", "pat_v2_"},
+			Regex: map[string]string{
+				"test": "!!?(?:?)[a-zA-Z0-9]{32}", // invalid regex
+			},
+		},
+	}
+
+	_, err := c.FromData(context.Background(), false, []byte("test"))
+	assert.Error(t, err)
+}
+
+func TestProductIndices(t *testing.T) {
+	tests := []struct {
+		name  string
+		input []int
+		want  [][]int
+	}{
+		{
+			name:  "zero",
+			input: []int{3, 0},
+			want:  nil,
+		},
+		{
+			name:  "one input",
+			input: []int{3},
+			want:  [][]int{{0}, {1}, {2}},
+		},
+		{
+			name:  "two inputs",
+			input: []int{3, 2},
+			want: [][]int{
+				{0, 0}, {1, 0}, {2, 0},
+				{0, 1}, {1, 1}, {2, 1},
+			},
+		},
+		{
+			name:  "three inputs",
+			input: []int{3, 2, 3},
+			want: [][]int{
+				{0, 0, 0}, {1, 0, 0}, {2, 0, 0},
+				{0, 1, 0}, {1, 1, 0}, {2, 1, 0},
+				{0, 0, 1}, {1, 0, 1}, {2, 0, 1},
+				{0, 1, 1}, {1, 1, 1}, {2, 1, 1},
+				{0, 0, 2}, {1, 0, 2}, {2, 0, 2},
+				{0, 1, 2}, {1, 1, 2}, {2, 1, 2},
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := productIndices(tt.input...)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func TestProductIndicesMax(t *testing.T) {
+	got := productIndices(2, 3, 4, 5, 6)
+	assert.GreaterOrEqual(t, 2*3*4*5*6, maxTotalMatches)
+	assert.Equal(t, maxTotalMatches, len(got))
+}
+
+func TestPermutateMatches(t *testing.T) {
+	tests := []struct {
+		name  string
+		input map[string][][]string
+		want  []map[string][]string
+	}{
+		{
+			name:  "two matches",
+			input: map[string][][]string{"foo": {{"matchA"}, {"matchB"}}, "bar": {{"matchC"}}},
+			want: []map[string][]string{
+				{"foo": {"matchA"}, "bar": {"matchC"}},
+				{"foo": {"matchB"}, "bar": {"matchC"}},
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := permutateMatches(tt.input)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func BenchmarkProductIndices(b *testing.B) {
+	for i := 0; i < b.N; i++ {
+		_ = productIndices(3, 2, 6)
+	}
+}
@@ -0,0 +1,44 @@
+package custom_detectors
+
+import (
+	"regexp"
+	"strconv"
+	"strings"
+)
+
+// nameGroupRegex matches `{ name . group }` ignoring any whitespace.
+var nameGroupRegex = regexp.MustCompile(`{\s*([a-zA-Z0-9-_]+)\s*(\.\s*[0-9]*)?\s*}`)
+
+// RegexVarString is a string with embedded {name.group} variables. A name may
+// only contain alphanumeric, hyphen, and underscore characters. Group is
+// optional but if provided it must be a non-negative integer. If the group is
+// omitted it defaults to 0.
+type RegexVarString struct {
+	original string
+	// map from name to group
+	variables map[string]int
+}
+
+func NewRegexVarString(original string) RegexVarString {
+	variables := make(map[string]int)
+
+	matches := nameGroupRegex.FindAllStringSubmatch(original, -1)
+	for _, match := range matches {
+		name, group := match[1], 0
+		// The second match will start with a period followed by any number
+		// of whitespace.
+		if len(match[2]) > 1 {
+			g, err := strconv.Atoi(strings.TrimSpace(match[2][1:]))
+			if err != nil {
+				continue
+			}
+			group = g
+		}
+		variables[name] = group
+	}
+
+	return RegexVarString{
+		original:  original,
+		variables: variables,
+	}
+}
@@ -0,0 +1,76 @@
+package custom_detectors
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestVarString(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    string
+		wantVars map[string]int
+	}{
+		{
+			name:     "empty",
+			input:    "{}",
+			wantVars: map[string]int{},
+		},
+		{
+			name:  "no subgroup",
+			input: "{hello}",
+			wantVars: map[string]int{
+				"hello": 0,
+			},
+		},
+		{
+			name:  "with subgroup",
+			input: "{hello.123}",
+			wantVars: map[string]int{
+				"hello": 123,
+			},
+		},
+		{
+			name:  "subgroup with spaces",
+			input: "{\thell0  . 123  }",
+			wantVars: map[string]int{
+				"hell0": 123,
+			},
+		},
+		{
+			name:  "multiple groups",
+			input: "foo {bar} {bazz.buzz} {buzz.2}",
+			wantVars: map[string]int{
+				"bar":  0,
+				"buzz": 2,
+			},
+		},
+		{
+			name:  "nested groups",
+			input: "{foo {bar}}",
+			wantVars: map[string]int{
+				"bar": 0,
+			},
+		},
+		{
+			name:  "decimal without number",
+			input: "{foo.}",
+			wantVars: map[string]int{
+				"foo": 0,
+			},
+		},
+		{
+			name:     "negative number",
+			input:    "{foo.-1}",
+			wantVars: map[string]int{},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := NewRegexVarString(tt.input)
+			assert.Equal(t, tt.input, got.original)
+			assert.Equal(t, tt.wantVars, got.variables)
+		})
+	}
+}
@@ -0,0 +1,109 @@
+package custom_detectors
+
+import (
+	"fmt"
+	"regexp"
+	"strconv"
+	"strings"
+)
+
+func ValidateKeywords(keywords []string) error {
+	if len(keywords) == 0 {
+		return fmt.Errorf("no keywords")
+	}
+
+	for _, keyword := range keywords {
+		if len(keyword) == 0 {
+			return fmt.Errorf("empty keyword")
+		}
+	}
+	return nil
+}
+
+func ValidateRegex(regex map[string]string) error {
+	if len(regex) == 0 {
+		return fmt.Errorf("no regex")
+	}
+	for name, reg := range regex {
+		if _, err := regexp.Compile(reg); err != nil {
+			return fmt.Errorf("regex '%s': %w", name, err)
+		}
+	}
+	return nil
+}
+
+func ValidateVerifyEndpoint(endpoint string, unsafe bool) error {
+	if len(endpoint) == 0 {
+		return fmt.Errorf("no endpoint")
+	}
+
+	if strings.HasPrefix(endpoint, "http://") && !unsafe {
+		return fmt.Errorf("http endpoint must have unsafe=true")
+	}
+	return nil
+}
+
+func ValidateVerifyHeaders(headers []string) error {
+	for _, header := range headers {
+		if !strings.Contains(header, ":") {
+			return fmt.Errorf("header %q must contain a colon", header)
+		}
+	}
+	return nil
+}
+
+func ValidateVerifyRanges(ranges []string) error {
+	const httpLowerRange = 100
+	const httpUpperRange = 599
+
+	for _, successRange := range ranges {
+		if !strings.Contains(successRange, "-") {
+			httpCode, err := strconv.Atoi(successRange)
+			if err != nil {
+				return fmt.Errorf("unable to convert http code to int %q", successRange)
+			}
+
+			if httpCode < httpLowerRange || httpCode > httpUpperRange {
+				return fmt.Errorf("invalid http status code %q", successRange)
+			}
+
+			continue
+		}
+
+		httpRange := strings.Split(successRange, "-")
+		if len(httpRange) != 2 {
+			return fmt.Errorf("invalid range format %q", successRange)
+		}
+
+		lowerBound, err := strconv.Atoi(httpRange[0])
+		if err != nil {
+			return fmt.Errorf("unable to convert lower bound to int %q", successRange)
+		}
+
+		upperBound, err := strconv.Atoi(httpRange[1])
+		if err != nil {
+			return fmt.Errorf("unable to convert upper bound to int %q", successRange)
+		}
+
+		if lowerBound > upperBound {
+			return fmt.Errorf("lower bound greater than upper bound on range %q", successRange)
+		}
+
+		if lowerBound < httpLowerRange || upperBound > httpUpperRange {
+			return fmt.Errorf("invalid http status code range %q", successRange)
+		}
+	}
+	return nil
+}
+
+func ValidateRegexVars(regex map[string]string, body ...string) error {
+	for _, b := range body {
+		matches := NewRegexVarString(b).variables
+		for match := range matches {
+			if _, ok := regex[match]; !ok {
+				return fmt.Errorf("body %q contains an unknown variable", b)
+			}
+		}
+	}
+	return nil
+}
@@ -0,0 +1,234 @@
+package custom_detectors
+
+import "testing"
+
+func TestCustomDetectorsKeywordValidation(t *testing.T) {
+	tests := []struct {
+		name    string
+		input   []string
+		wantErr bool
+	}{
+		{
+			name:    "Test empty list of keywords",
+			input:   []string{},
+			wantErr: true,
+		},
+		{
+			name:    "Test empty keyword",
+			input:   []string{""},
+			wantErr: true,
+		},
+		{
+			name:    "Test valid keywords",
+			input:   []string{"hello", "world"},
+			wantErr: false,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := ValidateKeywords(tt.input)
+
+			if (got != nil && !tt.wantErr) || (got == nil && tt.wantErr) {
+				t.Errorf("ValidateKeywords() error = %v, wantErr %v", got, tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestCustomDetectorsRegexValidation(t *testing.T) {
+	tests := []struct {
+		name    string
+		input   map[string]string
+		wantErr bool
+	}{
+		{
+			name: "Test list of keywords",
+			input: map[string]string{
+				"id_pat_example": "([a-zA-Z0-9]{32})",
+			},
+			wantErr: false,
+		},
+		{
+			name:    "Test empty list of keywords",
+			input:   map[string]string{},
+			wantErr: true,
+		},
+		{
+			name: "Test invalid regex",
+			input: map[string]string{
+				"test": "!!?(?:?)[a-zA-Z0-9]{32}",
+			},
+			wantErr: true,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := ValidateRegex(tt.input)
+
+			if (got != nil && !tt.wantErr) || (got == nil && tt.wantErr) {
+				t.Errorf("ValidateRegex() error = %v, wantErr %v", got, tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestCustomDetectorsVerifyEndpointValidation(t *testing.T) {
+	tests := []struct {
+		name     string
+		endpoint string
+		unsafe   bool
+		wantErr  bool
+	}{
+		{
+			name:     "Test http endpoint with unsafe flag",
+			endpoint: "http://localhost:8000/{id_pat_example}",
+			unsafe:   true,
+			wantErr:  false,
+		},
+		{
+			name:     "Test http endpoint without unsafe flag",
+			endpoint: "http://localhost:8000/{id_pat_example}",
+			unsafe:   false,
+			wantErr:  true,
+		},
+		{
+			name:     "Test https endpoint with unsafe flag",
+			endpoint: "https://localhost:8000/{id_pat_example}",
+			unsafe:   true,
+			wantErr:  false,
+		},
+		{
+			name:     "Test https endpoint without unsafe flag",
+			endpoint: "https://localhost:8000/{id_pat_example}",
+			unsafe:   false,
+			wantErr:  false,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := ValidateVerifyEndpoint(tt.endpoint, tt.unsafe)
+
+			if (got != nil && !tt.wantErr) || (got == nil && tt.wantErr) {
+				t.Errorf("ValidateVerifyEndpoint() error = %v, wantErr %v", got, tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestCustomDetectorsVerifyHeadersValidation(t *testing.T) {
+	tests := []struct {
+		name    string
+		headers []string
+		wantErr bool
+	}{
+		{
+			name:    "Test single header",
+			headers: []string{"Authorization: Bearer {secret_pat_example.0}"},
+			wantErr: false,
+		},
+		{
+			name:    "Test invalid header",
+			headers: []string{"Hello world"},
+			wantErr: true,
+		},
+		{
+			name:    "Test ugly header",
+			headers: []string{"Hello:::::::world::hi:"},
+			wantErr: false,
+		},
+		{
+			name:    "Test empty header",
+			headers: []string{},
+			wantErr: false,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := ValidateVerifyHeaders(tt.headers)
+
+			if (got != nil && !tt.wantErr) || (got == nil && tt.wantErr) {
+				t.Errorf("ValidateVerifyHeaders() error = %v, wantErr %v", got, tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestCustomDetectorsVerifyRangeValidation(t *testing.T) {
+	tests := []struct {
+		name    string
+		ranges  []string
+		wantErr bool
+	}{
+		{
+			name:    "Test multiple mixed ranges",
+			ranges:  []string{"200", "300-350"},
+			wantErr: false,
+		},
+		{
+			name:    "Test invalid non-number range",
+			ranges:  []string{"hi"},
+			wantErr: true,
+		},
+		{
+			name:    "Test invalid lower to upper range",
+			ranges:  []string{"200-100"},
+			wantErr: true,
+		},
+		{
+			name:    "Test invalid http range",
+			ranges:  []string{"400-1000"},
+			wantErr: true,
+		},
+		{
+			name:    "Test multiple ranges with invalid inputs",
+			ranges:  []string{"322", "hello-world", "100-200"},
+			wantErr: true,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := ValidateVerifyRanges(tt.ranges)
+
+			if (got != nil && !tt.wantErr) || (got == nil && tt.wantErr) {
+				t.Errorf("ValidateVerifyRanges() error = %v, wantErr %v", got, tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestCustomDetectorsVerifyRegexVarsValidation(t *testing.T) {
+	tests := []struct {
+		name    string
+		regex   map[string]string
+		body    string
+		wantErr bool
+	}{
+		{
+			name:    "Regex defined but not used in body",
+			regex:   map[string]string{"id": "[0-9]{1,10}", "id_pat_example": "([a-zA-Z0-9]{32})"},
+			body:    "hello world",
+			wantErr: false,
+		},
+		{
+			name:    "Regex defined and is used in body",
+			regex:   map[string]string{"id": "[0-9]{1,10}", "id_pat_example": "([a-zA-Z0-9]{32})"},
+			body:    "hello world {id}",
+			wantErr: false,
+		},
+		{
+			name:    "Regex var in body but not defined",
+			regex:   map[string]string{"id": "[0-9]{1,10}", "id_pat_example": "([a-zA-Z0-9]{32})"},
+			body:    "hello world {hello}",
+			wantErr: true,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := ValidateRegexVars(tt.regex, tt.body)
+
+			if (got != nil && !tt.wantErr) || (got == nil && tt.wantErr) {
+				t.Errorf("ValidateRegexVars() error = %v, wantErr %v", got, tt.wantErr)
+			}
+		})
+	}
+}
@@ -6,7 +6,7 @@ import (

 func DefaultDecoders() []Decoder {
 	return []Decoder{
-		&Plain{},
+		&UTF8{},
 		&Base64{},
 	}
 }
@@ -1,14 +0,0 @@
-package decoders
-
-import (
-	"github.com/trufflesecurity/trufflehog/v3/pkg/sources"
-)
-
-// Ensure the Decoder satisfies the interface at compile time
-var _ Decoder = (*Plain)(nil)
-
-type Plain struct{}
-
-func (d *Plain) FromChunk(chunk *sources.Chunk) *sources.Chunk {
-	return chunk
-}
@@ -0,0 +1,44 @@
+package decoders
+
+import (
+	"bytes"
+	"unicode/utf8"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/sources"
+)
+
+type UTF8 struct{}
+
+func (d *UTF8) FromChunk(chunk *sources.Chunk) *sources.Chunk {
+	if chunk == nil || len(chunk.Data) == 0 {
+		return nil
+	}
+
+	if !utf8.Valid(chunk.Data) {
+		chunk.Data = extractSubstrings(chunk.Data)
+		return chunk
+	}
+
+	return chunk
+}
+
+// extractSubstrings performs similarly to the strings binutil,
+// extacting contigous portions of printable characters that we care
+// about from some bytes
+func extractSubstrings(b []byte) []byte {
+	fields := bytes.FieldsFunc(b, func(r rune) bool {
+		// https://www.rapidtables.com/code/text/ascii-table.html
+		// split on anything that is not ascii space through tilde
+		return !(r > 31 && r < 127)
+	})
+
+	keep := [][]byte{}
+	for _, field := range fields {
+		// Remove fields shorter than 6 characters.
+		if bts := bytes.TrimSpace(field); len(bts) > 5 {
+			keep = append(keep, bts)
+		}
+	}
+
+	return bytes.Join(keep, []byte("\n"))
+}
@@ -0,0 +1,87 @@
+package decoders
+
+import (
+	"testing"
+
+	"github.com/kylelemons/godebug/pretty"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/sources"
+)
+
+func TestUTF8_FromChunk(t *testing.T) {
+	type args struct {
+		chunk *sources.Chunk
+	}
+	tests := []struct {
+		name    string
+		d       *UTF8
+		args    args
+		want    *sources.Chunk
+		wantErr bool
+	}{
+		{
+			name: "successful UTF8 decode",
+			d:    &UTF8{},
+			args: args{
+				chunk: &sources.Chunk{Data: []byte("plain 'ol chunk that should decode successfully")},
+			},
+			want:    &sources.Chunk{Data: []byte("plain 'ol chunk that should decode successfully")},
+			wantErr: false,
+		},
+		{
+			name: "successful binary decode",
+			d:    &UTF8{},
+			args: args{
+				chunk: &sources.Chunk{Data: []byte("\xf0\x28\x8c\x28 not-entirely utf8 chunk that should decode successfully")},
+			},
+			want:    &sources.Chunk{Data: []byte("( not-entirely utf8 chunk that should decode successfully")},
+			wantErr: false,
+		},
+		{
+			name: "unsuccessful decode",
+			d:    &UTF8{},
+			args: args{
+				chunk: nil,
+			},
+			want:    nil,
+			wantErr: false,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			d := &UTF8{}
+			got := d.FromChunk(tt.args.chunk)
+			if got != nil && tt.want != nil {
+				if diff := pretty.Compare(string(got.Data), string(tt.want.Data)); diff != "" {
+					t.Errorf("%s: Plain.FromChunk() diff: (-got +want)\n%s", tt.name, diff)
+				}
+			} else {
+				if diff := pretty.Compare(got, tt.want); diff != "" {
+					t.Errorf("%s: Plain.FromChunk() diff: (-got +want)\n%s", tt.name, diff)
+				}
+			}
+		})
+	}
+}
+
+var testBytes = []byte(`some words   with random spaces and
+	
+newlines with           
+arbitrary length           
+of
+
+	hey
+
+the lines themselves.
+
+and
+short
+words
+that
+go
+away.`)
+
+func Benchmark_extractSubstrings(b *testing.B) {
+	for i := 0; i < b.N; i++ {
+		extractSubstrings(testBytes)
+	}
+}
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -81,5 +81,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -68,5 +68,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -68,5 +68,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -80,5 +80,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result

 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -78,5 +78,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -81,5 +81,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result

 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -81,5 +81,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -71,5 +71,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -85,5 +85,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result

 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -68,5 +68,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -71,5 +71,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -79,5 +79,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -71,5 +71,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -74,5 +74,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -80,5 +80,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -72,5 +72,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -78,5 +78,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			results = append(results, s1)
 		}
 	}
-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -128,5 +128,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -69,5 +69,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -75,5 +75,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -86,5 +86,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -79,5 +79,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -80,5 +80,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -69,5 +69,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -80,7 +80,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }

 type Response struct {
@@ -82,5 +82,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result

 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -78,5 +78,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -81,5 +81,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -68,5 +68,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -2,12 +2,12 @@ package apilayer

 import (
 	"context"
-	"net/http"
-	"regexp"
-		"strings"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+	"net/http"
+	"regexp"
+	"strings"
 )

 type Scanner struct{}
@@ -18,7 +18,7 @@ var _ detectors.Detector = (*Scanner)(nil)
 var (
 	client = common.SaneHttpClient()

-	//Make sure that your group is surrounded in boundry characters such as below to reduce false positives
+	// Make sure that your group is surrounded in boundry characters such as below to reduce false positives
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"apilayer"}) + `\b([a-zA-Z0-9]{32})\b`)
 )

@@ -57,7 +57,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 				if res.StatusCode >= 200 && res.StatusCode < 300 {
 					s1.Verified = true
 				} else {
-					//This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key
+					// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}
@@ -68,5 +68,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -82,5 +82,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			results = append(results, s1)
 		}
 	}
-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -69,5 +69,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -90,5 +90,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -73,5 +73,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -74,5 +74,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -89,5 +89,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -81,5 +81,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -80,5 +80,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result

 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -69,5 +69,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -79,5 +79,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -88,5 +88,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -114,5 +114,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -80,5 +80,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -79,5 +79,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -69,5 +69,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -21,7 +21,7 @@ var (
 	client = common.SaneHttpClient()

 	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
-	//The number prefix increments for every Personal Access Token created.
+	// The number prefix increments for every Personal Access Token created.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"avaza"}) + `\b([0-9]+-[0-9a-f]{40})\b`)
 )

@@ -71,5 +71,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -72,5 +72,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -17,10 +17,35 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
 )

-type Scanner struct{}
+type scanner struct {
+	skipIDs map[string]struct{}
+}

-// Ensure the Scanner satisfies the interface at compile time.
-var _ detectors.Detector = (*Scanner)(nil)
+func New(opts ...func(*scanner)) *scanner {
+	scanner := &scanner{
+		skipIDs: map[string]struct{}{},
+	}
+	for _, opt := range opts {
+
+		opt(scanner)
+	}
+
+	return scanner
+}
+
+func WithSkipIDs(skipIDs []string) func(*scanner) {
+	return func(s *scanner) {
+		ids := map[string]struct{}{}
+		for _, id := range skipIDs {
+			ids[id] = struct{}{}
+		}
+
+		s.skipIDs = ids
+	}
+}
+
+// Ensure the scanner satisfies the interface at compile time.
+var _ detectors.Detector = (*scanner)(nil)

 var (
 	client = common.SaneHttpClient()
@@ -37,7 +62,7 @@ var (

 // Keywords are used for efficiently pre-filtering chunks.
 // Use identifiers in the secret preferably, or the provider name.
-func (s Scanner) Keywords() []string {
+func (s scanner) Keywords() []string {
 	return []string{
 		"AKIA",
 		"ABIA",
@@ -60,7 +85,7 @@ func GetHMAC(key []byte, data []byte) []byte {
 }

 // FromData will find and optionally verify AWS secrets in a given set of bytes.
-func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
+func (s scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
 	dataStr := string(data)

 	idMatches := idPat.FindAllStringSubmatch(dataStr, -1)
@@ -72,6 +97,12 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 		resIDMatch := strings.TrimSpace(idMatch[1])

+		if s.skipIDs != nil {
+			if _, ok := s.skipIDs[resIDMatch]; ok {
+				continue
+			}
+		}
+
 		for _, secretMatch := range secretMatches {
 			if len(secretMatch) != 2 {
 				continue
@@ -39,14 +39,14 @@ func TestAWS_FromChunk(t *testing.T) {
 	}
 	tests := []struct {
 		name    string
-		s       Scanner
+		s       scanner
 		args    args
 		want    []detectors.Result
 		wantErr bool
 	}{
 		{
 			name: "found, verified",
-			s:    Scanner{},
+			s:    scanner{},
 			args: args{
 				ctx:    context.Background(),
 				data:   []byte(fmt.Sprintf("You can find a aws secret %s within aws %s", secret, id)),
@@ -68,7 +68,7 @@ func TestAWS_FromChunk(t *testing.T) {
 		},
 		{
 			name: "found, unverified",
-			s:    Scanner{},
+			s:    scanner{},
 			args: args{
 				ctx:    context.Background(),
 				data:   []byte(fmt.Sprintf("You can find a aws secret %s within aws %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
@@ -86,7 +86,7 @@ func TestAWS_FromChunk(t *testing.T) {
 		},
 		{
 			name: "not found",
-			s:    Scanner{},
+			s:    scanner{},
 			args: args{
 				ctx:    context.Background(),
 				data:   []byte("You cannot find the secret within"),
@@ -97,7 +97,7 @@ func TestAWS_FromChunk(t *testing.T) {
 		},
 		{
 			name: "found two, one included for every ID found",
-			s:    Scanner{},
+			s:    scanner{},
 			args: args{
 				ctx:    context.Background(),
 				data:   []byte(fmt.Sprintf("The verified ID is %s with a secret of %s, but the unverified ID is %s and this is the secret %s", id, secret, inactiveID, inactiveSecret)),
@@ -124,7 +124,7 @@ func TestAWS_FromChunk(t *testing.T) {
 		},
 		{
 			name: "not found, because unverified secret was a hash",
-			s:    Scanner{},
+			s:    scanner{},
 			args: args{
 				ctx:    context.Background(),
 				data:   []byte(fmt.Sprintf("You can find a aws secret %s within aws %s but not valid", hash, id)), // The secret would satisfy the regex but be filtered out after not passing validation.
@@ -135,7 +135,7 @@ func TestAWS_FromChunk(t *testing.T) {
 		},
 		{
 			name: "found two, returned both because the active secret for one paired with the inactive ID, despite the hash",
-			s:    Scanner{},
+			s:    scanner{},
 			args: args{
 				ctx:    context.Background(),
 				data:   []byte(fmt.Sprintf("The verified ID is %s with a secret of %s, but the unverified ID is %s and the secret is this hash %s", id, secret, inactiveID, hash)),
@@ -162,7 +162,7 @@ func TestAWS_FromChunk(t *testing.T) {
 		},
 		{
 			name: "found, unverified, with leading +",
-			s:    Scanner{},
+			s:    scanner{},
 			args: args{
 				ctx:    context.Background(),
 				data:   []byte(fmt.Sprintf("You can find a aws secret %s within aws %s but not valid", "+HaNv9cTwheDKGJaws/+BMF2GgybQgBWdhcOOdfF", id)), // the secret would satisfy the regex but not pass validation
@@ -177,10 +177,24 @@ func TestAWS_FromChunk(t *testing.T) {
 			},
 			wantErr: false,
 		},
+		{
+			name: "skipped",
+			s: scanner{
+				skipIDs: map[string]struct{}{
+					"AKIAWARWQKZNHMZBLY4I": {},
+				},
+			},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a aws secret %s within aws %s but not valid", "+HaNv9cTwheDKGJaws/+BMF2GgybQgBWdhcOOdfF", id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			wantErr: false,
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			s := Scanner{}
+			s := tt.s
 			got, err := s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
 			if (err != nil) != tt.wantErr {
 				t.Errorf("AWS.FromData() error = %v, wantErr %v", err, tt.wantErr)
@@ -201,7 +215,7 @@ func TestAWS_FromChunk(t *testing.T) {

 func BenchmarkFromData(benchmark *testing.B) {
 	ctx := context.Background()
-	s := Scanner{}
+	s := scanner{}
 	for name, data := range detectors.MustGetBenchmarkData() {
 		benchmark.Run(name, func(b *testing.B) {
 			for n := 0; n < b.N; n++ {
@@ -69,5 +69,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -79,5 +79,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -83,5 +83,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -70,5 +70,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -77,5 +77,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -69,5 +69,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -75,5 +75,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -2,11 +2,11 @@ package besnappy

 import (
 	"context"
+	b64 "encoding/base64"
 	"fmt"
 	"net/http"
 	"regexp"
 	"strings"
-	b64 "encoding/base64"

 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -21,7 +21,7 @@ var _ detectors.Detector = (*Scanner)(nil)
 var (
 	client = common.SaneHttpClient()

-	//Make sure that your group is surrounded in boundry characters such as below to reduce false positives
+	// Make sure that your group is surrounded in boundry characters such as below to reduce false positives
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"besnappy"}) + `\b([a-f0-9]{64})\b`)
 )

@@ -61,7 +61,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 				if res.StatusCode >= 200 && res.StatusCode < 300 {
 					s1.Verified = true
 				} else {
-					//This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key
+					// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}
@@ -72,5 +72,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -75,5 +75,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -80,5 +80,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
@@ -74,5 +74,5 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		results = append(results, s1)
 	}

-	return detectors.CleanResults(results), nil
+	return results, nil
 }
--- a/Show More
+++ b/Show More