update jira detector to match new variable tokens (#1720)

* update jira detector to match new variable tokens * add versioned interface * use _v2 format for naming packages w. versioner - also added documentation for internal/external contrib. * migrate jira and jira_v2 secrets tests to newer version * add v2 specific domain and email * add support for tri-state verification --------- Co-authored-by: Zubair Khan <zkhan124@umd.edu>
2023-09-01 12:14:36 -04:00
parent 78bbb89a30
commit 2e4b17d3f4
6 changed files with 272 additions and 3 deletions
@@ -44,6 +44,18 @@ If you think that something should be included outside of these guidelines, plea
 - Go 1.17+
 - Make

+### Adding New Token Formats to an Existing Scanner
+
+In some instances, services will update their token format, requiring a new regex to properly detect secrets in addition to supporting the previous token format. Accomodating this can be done without adding a net-new detector. [We provide a `Versioner` interface](https://github.com/trufflesecurity/trufflehog/blob/e18cfd5e0af1469a9f05b8d5732bcc94c39da49c/pkg/detectors/detectors.go#L30) that can be implemented.
+
+1. Create a copy of the package and append `_v2` to the package and file names. Ex: `<packagename>/` -> `<packagename>_v2`, `<packagename>.go` -> `<packagename>_v2.go`
+
+Note: Be sure to update the tests to reference the new secret values in GSM, or the tests will fail.
+
+2. Implement the `Versioner` interface. [GitHub example implementation.](/pkg/detectors/github_old/github_old.go#L22)
+
+3. Proceed from step 3 of [Creating a new Secret Scanner](#creating-a-new-secret-scanner)
+
 ### Creating a new Secret Scanner

 1. Identify the Secret Detector name from the [/proto/detectors.proto](/proto/detectors.proto) `DetectorType` enum.
@@ -96,7 +108,7 @@ Do not embed test credentials in the test code. Instead, use GCP Secrets Manager
   Note: `/tmp/s` is a valid path on Linux. You will need to change that for Windows or OSX, otherwise you will see an error. On Windows you will also need to install [WSL](https://docs.microsoft.com/en-us/windows/wsl/install).

   ```bash
-   gcloud secrets versions access --project trufflehog-testing --secret detectors3 latest > /tmp/s
+   gcloud secrets versions access --project trufflehog-testing --secret detectors5 latest > /tmp/s
   ```

 2. Add the secret that you need for testing.
@@ -113,8 +125,9 @@ Do not embed test credentials in the test code. Instead, use GCP Secrets Manager
 3. Update the secret version with your modification.

   ```bash
-   gcloud secrets versions add --project trufflehog-testing detectors3 --data-file /tmp/s
+   gcloud secrets versions add --project trufflehog-testing detectors5 --data-file /tmp/s
   ```
+   Note: We increment the detectors file name `detectors(n+1)` once the previous one exceeds the max size allowed by GSM (65kb).

 4. Access the secret value as shown in the [example code](pkg/detectors/heroku/heroku_test.go).

@@ -40,6 +40,18 @@ If you think that something should be included outside of these guidelines, plea
 - Go 1.17+
 - Make

+### Adding New Token Formats to an Existing Scanner
+
+In some instances, services will update their token format, requiring a new regex to properly detect secrets in addition to supporting the previous token format. Accomodating this can be done without adding a net-new detector. [We provide a `Versioner` interface](https://github.com/trufflesecurity/trufflehog/blob/e18cfd5e0af1469a9f05b8d5732bcc94c39da49c/pkg/detectors/detectors.go#L30) that can be implemented.
+
+1. Create a copy of the package and append `_v2` to the package and file names. Ex: `<packagename>/` -> `<packagename>_v2`, `<packagename>.go` -> `<packagename>_v2.go`
+
+Note: Be sure to update the tests to reference the new secret values in GSM, or the tests will fail.
+
+2. Implement the `Versioner` interface. [GitHub example implementation.](/pkg/detectors/github_old/github_old.go#L22)
+
+3. Proceed from step 3 of [Creating a new Secret Scanner](#creating-a-new-secret-scanner)
+
 ### Creating a new Secret Scanner

 1. Identify the Secret Detector name from the [/proto/detectors.proto](/proto/detectors.proto) `DetectorType` enum. If necessary, run `make protos` when adding new ones.
@@ -17,6 +17,9 @@ type Scanner struct{}

 // Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
+var _ detectors.Versioner = (*Scanner)(nil)
+
+func (Scanner) Version() int            { return 1 }

 var (
 	client = common.SaneHttpClient()
@@ -19,7 +19,7 @@ import (
 func TestJiraToken_FromChunk(t *testing.T) {
 	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
 	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors3")
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors5")
 	if err != nil {
 		t.Fatalf("could not get test secrets from GCP: %s", err)
 	}
@@ -0,0 +1,118 @@
+package jiratoken_v2
+
+import (
+	"context"
+	b64 "encoding/base64"
+	"fmt"
+	"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"
+)
+
+type Scanner struct{}
+
+// Ensure the Scanner satisfies the interface at compile time.
+var _ detectors.Detector = (*Scanner)(nil)
+var _ detectors.Versioner = (*Scanner)(nil)
+
+func (Scanner) Version() int            { return 2 }
+
+var (
+	client = common.SaneHttpClient()
+
+	// https://support.atlassian.com/atlassian-account/docs/manage-api-tokens-for-your-atlassian-account/
+	// Tokens created after Jan 18 2023 use a variable length
+	tokenPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"jira"}) + `\b([A-Za-z0-9+/=_-]+=[A-Za-z0-9]{8})\b`)
+	domainPat = regexp.MustCompile(detectors.PrefixRegex([]string{"jira"}) + `\b([a-zA-Z-0-9]{5,24}\.[a-zA-Z-0-9]{3,16}\.[a-zA-Z-0-9]{3,16})\b`)
+	emailPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"jira"}) + `\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b`)
+)
+
+const (
+	failedAuth           = "AUTHENTICATED_FAILED"
+	loginReasonHeaderKey = "X-Seraph-LoginReason"
+)
+
+// Keywords are used for efficiently pre-filtering chunks.
+// Use identifiers in the secret preferably, or the provider name.
+func (s Scanner) Keywords() []string {
+	return []string{"jira"}
+}
+
+// FromData will find and optionally verify JiraToken secrets in a given set of bytes.
+func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
+	dataStr := string(data)
+
+	tokens := tokenPat.FindAllStringSubmatch(dataStr, -1)
+	domains := domainPat.FindAllStringSubmatch(dataStr, -1)
+	emails := emailPat.FindAllStringSubmatch(dataStr, -1)
+
+	for _, email := range emails {
+		email = strings.Split(email[0], " ")
+		if len(email) != 2 {
+			continue
+		}
+		resEmail := strings.TrimSpace(email[1])
+		for _, token := range tokens {
+			if len(token) != 2 {
+				continue
+			}
+			resToken := strings.TrimSpace(token[1])
+			for _, domain := range domains {
+				if len(domain) != 2 {
+					continue
+				}
+				resDomain := strings.TrimSpace(domain[1])
+
+				s1 := detectors.Result{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Raw:          []byte(resToken),
+					RawV2:        []byte(fmt.Sprintf("%s:%s:%s", resEmail, resToken, resDomain)),
+				}
+
+				if verify {
+					data := fmt.Sprintf("%s:%s", resEmail, resToken)
+					sEnc := b64.StdEncoding.EncodeToString([]byte(data))
+					req, err := http.NewRequestWithContext(ctx, "GET", "https://"+resDomain+"/rest/api/3/dashboard", nil)
+					if err != nil {
+						continue
+					}
+					req.Header.Add("Accept", "application/json")
+					req.Header.Add("Authorization", fmt.Sprintf("Basic %s", sEnc))
+					res, err := client.Do(req)
+					if err == nil {
+						defer res.Body.Close()
+
+						// If the request is successful and the login reason is not failed authentication, then the token is valid.
+						// This is because Jira returns a 200 status code even if the token is invalid.
+						// Jira returns a default dashboard page.
+						if (res.StatusCode >= 200 && res.StatusCode < 300) && res.Header.Get(loginReasonHeaderKey) != failedAuth {
+							s1.Verified = true
+						} else {
+							s1.VerificationError = err
+						}
+					}
+				}
+
+				if !s1.Verified {
+					if detectors.IsKnownFalsePositive(string(s1.Raw), detectors.DefaultFalsePositives, true) {
+						continue
+					}
+				}
+
+				results = append(results, s1)
+
+			}
+
+		}
+	}
+
+	return results, nil
+}
+
+func (s Scanner) Type() detectorspb.DetectorType {
+	return detectorspb.DetectorType_JiraToken
+}
@@ -0,0 +1,123 @@
+//go:build detectors
+// +build detectors
+
+package jiratoken_v2
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/kylelemons/godebug/pretty"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestJiraToken_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors5")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	token := testSecrets.MustGetField("JIRA_V2_TOKEN")
+	inactiveToken := testSecrets.MustGetField("JIRA_V2_INACTIVE")
+	email := testSecrets.MustGetField("JIRA_V2_EMAIL")
+	domain := testSecrets.MustGetField("JIRA_V2_DOMAIN")
+
+	type args struct {
+		ctx    context.Context
+		data   []byte
+		verify bool
+	}
+	tests := []struct {
+		name    string
+		s       Scanner
+		args    args
+		want    []detectors.Result
+		wantErr bool
+	}{
+		{
+			name: "found, verified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s with jira %s", token, email, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a jira secret %s within jira %s but not jira %s valid", inactiveToken, email, domain)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_JiraToken,
+					Verified:     false,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "not found",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte("You cannot find the secret within"),
+				verify: true,
+			},
+			want:    nil,
+			wantErr: false,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			s := Scanner{}
+			got, err := s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("JiraToken.FromData() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			for i := range got {
+				if len(got[i].Raw) == 0 {
+					t.Fatalf("no raw secret present: \n %+v", got[i])
+				}
+				got[i].Raw = nil
+				got[i].RawV2 = nil
+			}
+			if diff := pretty.Compare(got, tt.want); diff != "" {
+				t.Errorf("JiraToken.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
+			}
+		})
+	}
+}
+
+func BenchmarkFromData(benchmark *testing.B) {
+	ctx := context.Background()
+	s := Scanner{}
+	for name, data := range detectors.MustGetBenchmarkData() {
+		benchmark.Run(name, func(b *testing.B) {
+			b.ResetTimer()
+			for n := 0; n < b.N; n++ {
+				_, err := s.FromData(ctx, false, data)
+				if err != nil {
+					b.Fatal(err)
+				}
+			}
+		})
+	}
+}