PR 2 of 40

README.md

@@ -32,7 +32,7 @@ Have questions? Feedback? Jump in slack or discord and hang out with us
 
 Join our [Slack Community](https://join.slack.com/t/trufflehog-community/shared_invite/zt-pw2qbi43-Aa86hkiimstfdKH9UCpPzQ)
 
-Join the [Secret Scanning Discord](https://discord.gg/8Hzbrnkr7E)
+Join the [Secret Scanning Discord](https://discord.gg/sydS6AHTUP)
 
 # :tv: Demo
 

pkg/detectors/appcues/appcues.go

@@ -1,11 +1,11 @@
 package appcues
 
 import (
+	"bytes"
 	"context"
 	"fmt"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -20,64 +20,59 @@ var _ detectors.Detector = (*Scanner)(nil)
 var (
 	client = common.SaneHttpClient()
 
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"appcues"}) + `\b([a-z0-9-]{36})\b`)
 	userPat = regexp.MustCompile(detectors.PrefixRegex([]string{"appcues"}) + `\b([a-z0-9-]{39})\b`)
 	idPat   = regexp.MustCompile(detectors.PrefixRegex([]string{"appcues"}) + `\b([0-9]{5})\b`)
 )
 
-// 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{"appcues"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("appcues")}
 }
 
-// FromData will find and optionally verify Appcues 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)
 
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
-	userMatches := userPat.FindAllStringSubmatch(dataStr, -1)
-	idMatches := idPat.FindAllStringSubmatch(dataStr, -1)
+	keyMatches := keyPat.FindAllSubmatch(data, -1)
+	userMatches := userPat.FindAllSubmatch(data, -1)
+	idMatches := idPat.FindAllSubmatch(data, -1)
 
-	for _, match := range matches {
+	for _, match := range keyMatches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		for _, userMatch := range userMatches {
 			if len(userMatch) != 2 {
 				continue
 			}
 
-			resUserMatch := strings.TrimSpace(userMatch[1])
+			resUserMatch := bytes.TrimSpace(userMatch[1])
 
 			for _, idMatch := range idMatches {
 				if len(idMatch) != 2 {
 					continue
 				}
 
-				resIdMatch := strings.TrimSpace(idMatch[1])
+				resIdMatch := bytes.TrimSpace(idMatch[1])
 
 				s1 := detectors.Result{
 					DetectorType: detectorspb.DetectorType_Appcues,
-					Raw:          []byte(resMatch),
-					RawV2:        []byte(resMatch + resUserMatch),
+					Raw:          resMatch,
+					RawV2:        append(resMatch, resUserMatch...),
 				}
+
 				if verify {
-					req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.appcues.com/v2/accounts/%s/flows", resIdMatch), nil)
+					req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.appcues.com/v2/accounts/%s/flows", string(resIdMatch)), nil)
 					if err != nil {
 						continue
 					}
-					req.SetBasicAuth(resUserMatch, resMatch)
+					req.SetBasicAuth(string(resUserMatch), string(resMatch))
 					res, err := client.Do(req)
 					if err == nil {
 						defer res.Body.Close()
 						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.
 							if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 								continue
 							}

pkg/detectors/appfollow/appfollow.go

@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -15,42 +14,35 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
 	client = common.SaneHttpClient()
-
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"appfollow"}) + `\b([0-9A-Za-z]{20})\b`)
 )
 
-// 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{"appfollow"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("appfollow")}
 }
 
-// FromData will find and optionally verify Appfollow 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+
+		resMatch := match[1]
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_Appfollow,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
-			data := fmt.Sprintf("%s:", resMatch)
-			sEnc := b64.StdEncoding.EncodeToString([]byte(data))
+			data := append(resMatch, ':')
+			sEnc := b64.StdEncoding.EncodeToString(data)
 			req, err := http.NewRequestWithContext(ctx, "GET", "https://api.appfollow.io/test", nil)
 			if err != nil {
 				continue
@@ -62,7 +54,6 @@ 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.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/appointedd/appointedd.go

@@ -1,11 +1,11 @@
 package appointedd
 
 import (
+	"bytes"
 	"context"
 	"io"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,66 +14,53 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
 	client = common.SaneHttpClient()
-
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"appointedd"}) + `\b([a-zA-Z0-9=+]{88})`)
 )
 
-// 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{"appointedd"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("appointedd")}
 }
 
-// FromData will find and optionally verify appointedd 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_Appointedd,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 		if verify {
 			req, err := http.NewRequestWithContext(ctx, "GET", "https://api.appointedd.com/v1/availability/slots", nil)
 			if err != nil {
 				continue
 			}
-			req.Header.Add("X-API-KEY", resMatch)
+			req.Header.Add("X-API-KEY", string(resMatch))
 			res, err := client.Do(req)
 			if err == nil {
 				defer res.Body.Close()
-				bodyBytes, err := io.ReadAll(res.Body)
-				if err != nil {
-					continue
-				}
-				body := string(bodyBytes)
 
-				if strings.Contains(body, "total") {
-					s1.Verified = true
-				} else {
-					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
-						continue
+				if bodyBytes, err := io.ReadAll(res.Body); err == nil {
+					if bytes.Contains(bodyBytes, []byte("total")) {
+						s1.Verified = true
+					} else {
+						if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
+							continue
+						}
 					}
 				}
 			}
 		}
-
 		results = append(results, s1)
 	}
-
 	return results, nil
 }
 

pkg/detectors/appsynergy/appsynergy.go

@@ -1,11 +1,11 @@
 package appsynergy
 
 import (
+	"bytes"
 	"context"
 	"fmt"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,42 +14,34 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
 	client = common.SaneHttpClient()
-
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"appsynergy"}) + `\b([a-z0-9]{64})\b`)
 )
 
-// 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{"appsynergy"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("appsynergy")}
 }
 
-// FromData will find and optionally verify AppSynergy 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_AppSynergy,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
-			payload := strings.NewReader(`{"html":"<html><body><h1>Hello World</h1></body></html>","filename":"HelloWorld.pdf"}`)
-			req, err := http.NewRequestWithContext(ctx, "POST", fmt.Sprintf("https://www.appsynergy.com/api?action=HTML2PDF&apiKey=%s", resMatch), payload)
+			payload := bytes.NewBuffer([]byte(`{"html":"<html><body><h1>Hello World</h1></body></html>","filename":"HelloWorld.pdf"}`))
+			req, err := http.NewRequestWithContext(ctx, "POST", fmt.Sprintf("https://www.appsynergy.com/api?action=HTML2PDF&apiKey=%s", string(resMatch)), payload)
 			if err != nil {
 				continue
 			}
@@ -59,7 +51,6 @@ 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.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/apptivo/apptivo.go

@@ -1,12 +1,13 @@
 package apptivo
 
 import (
+	"bytes"
 	"context"
 	"fmt"
-	"io"
 	"net/http"
 	"regexp"
-	"strings"
+
+	"io/ioutil"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -15,60 +16,52 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
 	client = common.SaneHttpClient()
 
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"apptivo"}) + `\b([a-z0-9-]{36})\b`)
 	idPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"apptivo"}) + `\b([a-zA-Z0-9-]{32})\b`)
 )
 
-// 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{"apptivo"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("apptivo")}
 }
 
-// FromData will find and optionally verify Apptivo 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
-	idMatches := idPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
+	idMatches := idPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 		for _, idMatch := range idMatches {
 			if len(idMatch) != 2 {
 				continue
 			}
-			resIdMatch := strings.TrimSpace(idMatch[1])
+			resIdMatch := bytes.TrimSpace(idMatch[1])
 
 			s1 := detectors.Result{
 				DetectorType: detectorspb.DetectorType_Apptivo,
-				Raw:          []byte(resMatch),
-				RawV2:        []byte(resMatch + resIdMatch),
+				Raw:          resMatch,
+				RawV2:        append(resMatch, resIdMatch...),
 			}
 
 			if verify {
-				req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.apptivo.com/app/dao/v6/leads?a=getConfigData&apiKey=%s&accessKey=%s", resMatch, resIdMatch), nil)
+				req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.apptivo.com/app/dao/v6/leads?a=getConfigData&apiKey=%s&accessKey=%s", string(resMatch), string(resIdMatch)), nil)
 				if err != nil {
 					continue
 				}
 				res, err := client.Do(req)
 				if err == nil {
-					bodyBytes, err := io.ReadAll(res.Body)
+					bodyBytes, err := ioutil.ReadAll(res.Body)
 					if err != nil {
 						continue
 					}
-					bodyString := string(bodyBytes)
-					validResponse := strings.Contains(bodyString, `displayName`)
+					validResponse := bytes.Contains(bodyBytes, []byte(`displayName`))
 					defer res.Body.Close()
 					if res.StatusCode >= 200 && res.StatusCode < 300 {
 						if validResponse {
@@ -77,7 +70,6 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 							s1.Verified = false
 						}
 					} 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.
 						if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 							continue
 						}

pkg/detectors/artifactory/artifactory.go

@@ -1,10 +1,10 @@
 package artifactory
 
 import (
+	"bytes"
 	"context"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -19,58 +19,54 @@ var _ detectors.Detector = (*Scanner)(nil)
 var (
 	client = common.SaneHttpClient()
 
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
+	// Keep the regexp patterns unchanged
 	keyPat = regexp.MustCompile(`\b([a-zA-Z0-9]{73})`)
 	URLPat = regexp.MustCompile(`\b([A-Za-z0-9](?:[A-Za-z0-9\-]{0,61}[A-Za-z0-9])\.jfrog\.io)`)
 )
 
 // 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{"artifactory"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("artifactory")}
 }
 
 // FromData will find and optionally verify Artifactory 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)
-	URLmatches := URLPat.FindAllStringSubmatch(dataStr, -1)
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	URLmatches := URLPat.FindAllSubmatch(data, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
+
+	var resURLMatch []byte
 
-	resURLMatch := ""
 	for _, URLmatch := range URLmatches {
 		if len(URLmatch) != 2 {
 			continue
 		}
-		resURLMatch = strings.TrimSpace(URLmatch[1])
-
+		resURLMatch = bytes.TrimSpace(URLmatch[1])
 	}
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_ArtifactoryAccessToken,
-			Raw:          []byte(resMatch),
-			RawV2:        []byte(resMatch + resURLMatch),
+			Raw:          resMatch,
+			RawV2:        append(resMatch, resURLMatch...),
 		}
 
 		if verify {
-			req, err := http.NewRequestWithContext(ctx, "GET", "https://"+resURLMatch+"/artifactory/api/storageinfo", nil)
+			req, err := http.NewRequestWithContext(ctx, "GET", "https://"+string(resURLMatch)+"/artifactory/api/storageinfo", nil)
 			if err != nil {
 				continue
 			}
-
-			req.Header.Add("X-JFrog-Art-Api", resMatch)
+			req.Header.Add("X-JFrog-Art-Api", string(resMatch))
 			res, err := client.Do(req)
 			if err == nil {
 				defer res.Body.Close()
 				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.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/artsy/artsy.go

@@ -1,10 +1,10 @@
 package artsy
 
 import (
+	"bytes"
 	"context"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -13,51 +13,44 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
 	client = common.SaneHttpClient()
 
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"artsy"}) + `\b([0-9a-zA-Z]{32})\b`)
 	idPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"artsy"}) + `\b([0-9a-zA-Z]{20})\b`)
 )
 
-// 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{"artsy"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("artsy")}
 }
 
-// FromData will find and optionally verify Artsy 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
-	idmatches := idPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
+	idmatches := idPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
 
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		for _, idmatch := range idmatches {
 			if len(idmatch) != 2 {
 				continue
 			}
-			resIdMatch := strings.TrimSpace(idmatch[1])
+			resIdMatch := bytes.TrimSpace(idmatch[1])
 
 			s1 := detectors.Result{
 				DetectorType: detectorspb.DetectorType_Artsy,
-				Raw:          []byte(resMatch),
-				RawV2:        []byte(resMatch + resIdMatch),
+				Raw:          resMatch,
+				RawV2:        append(resMatch, resIdMatch...),
 			}
 
 			if verify {
-				req, err := http.NewRequestWithContext(ctx, "POST", "https://api.artsy.net/api/tokens/xapp_token?client_id="+resIdMatch+"&client_secret="+resMatch, nil)
+				req, err := http.NewRequestWithContext(ctx, "POST", "https://api.artsy.net/api/tokens/xapp_token?client_id="+string(resIdMatch)+"&client_secret="+string(resMatch), nil)
 				if err != nil {
 					continue
 				}
@@ -67,8 +60,7 @@ 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.
-						if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
+						if detectors.IsKnownFalsePositive(bytes.Join([][]byte{resMatch, resIdMatch}, nil), detectors.DefaultFalsePositives, true) {
 							continue
 						}
 					}
@@ -77,7 +69,6 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 
 			results = append(results, s1)
 		}
-
 	}
 
 	return results, nil

pkg/detectors/asanaoauth/asanaoauth.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -20,31 +19,25 @@ var _ detectors.Detector = (*Scanner)(nil)
 var (
 	client = common.SaneHttpClient()
 
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"asana"}) + `\b([a-z\/:0-9]{51})\b`)
 )
 
-// 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{"asana"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("asana")}
 }
 
-// FromData will find and optionally verify AsanaOauth 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := match[1]
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_AsanaOauth,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
@@ -52,14 +45,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			if err != nil {
 				continue
 			}
-			req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", resMatch))
+			req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", string(resMatch)))
 			res, err := client.Do(req)
-			if err == nil {
+			if err == nil && res.Body != nil {
 				defer res.Body.Close()
 				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.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/asanapersonalaccesstoken/asanapersonalaccesstoken.go

@@ -1,11 +1,11 @@
 package asanapersonalaccesstoken
 
 import (
+	"bytes"
 	"context"
 	"fmt"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,7 +14,6 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
@@ -23,27 +22,22 @@ var (
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"asana"}) + `\b([0-9]{1,}\/[0-9]{16,}:[A-Za-z0-9]{32,})\b`)
 )
 
-// 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{"asana"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("asana")}
 }
 
-// FromData will find and optionally verify AsanaPersonalAccessToken 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_AsanaPersonalAccessToken,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
@@ -51,14 +45,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			if err != nil {
 				continue
 			}
-			req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", resMatch))
+			req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", string(resMatch)))
 			res, err := client.Do(req)
 			if err == nil {
 				defer res.Body.Close()
 				if res.StatusCode >= 200 && res.StatusCode < 300 {
 					s1.Verified = true
 				} else {
-
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/assemblyai/assemblyai.go

@@ -1,10 +1,10 @@
 package assemblyai
 
 import (
+	"bytes"
 	"context"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -19,31 +19,28 @@ var _ detectors.Detector = (*Scanner)(nil)
 var (
 	client = common.SaneHttpClient()
 
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
+	// Keep the regexp patterns unchanged
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"assemblyai"}) + `\b([0-9a-z]{32})\b`)
 )
 
 // 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{"assemblyai"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("assemblyai")}
 }
 
 // FromData will find and optionally verify Assemblyai 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_AssemblyAI,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
@@ -52,14 +49,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 				continue
 			}
 			req.Header.Add("Content-Type", "application/json")
-			req.Header.Add("Authorization", resMatch)
+			req.Header.Add("Authorization", string(resMatch))
 			res, err := client.Do(req)
 			if err == nil {
 				defer res.Body.Close()
 				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.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/atera/atera.go

@@ -1,10 +1,10 @@
 package atera
 
 import (
+	"bytes"
 	"context"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -18,32 +18,27 @@ var _ detectors.Detector = (*Scanner)(nil)
 
 var (
 	client = common.SaneHttpClient()
-
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
-	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"atera"}) + `\b([[0-9a-z]{32})\b`)
+	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"atera"}) + `\b([0-9a-z]{32})\b`)
 )
 
 // 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{"atera"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("atera")}
 }
 
 // FromData will find and optionally verify Atera 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_Atera,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
@@ -52,14 +47,14 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 				continue
 			}
 			req.Header.Add("Accept", "application/json")
-			req.Header.Add("X-API-KEY", resMatch)
+			req.Header.Add("X-API-KEY", string(resMatch))
 			res, err := client.Do(req)
 			if err == nil {
 				defer res.Body.Close()
 				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.
+					// Consider adding the []byte conversion here if the input also changed to a []byte.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/audd/audd.go

@@ -1,12 +1,12 @@
 package audd
 
 import (
+	"bytes"
 	"context"
 	"fmt"
 	"io"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,30 +26,26 @@ var (
 )
 
 // 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{"audd"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("audd")}
 }
 
-// FromData will find and optionally verify Audd 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_Audd,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
-			req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.audd.io/setCallbackUrl/?api_token=%s&url=https://yourwebsite.com/callbacks_handler/", resMatch), nil)
+			req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.audd.io/setCallbackUrl/?api_token=%s&url=https://yourwebsite.com/callbacks_handler/", string(resMatch)), nil)
 			if err != nil {
 				continue
 			}
@@ -57,9 +53,8 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			if err == nil {
 				bodyBytes, err := io.ReadAll(res.Body)
 				if err == nil {
-					bodyString := string(bodyBytes)
-					validResponse := strings.Contains(bodyString, `"status":"success"`)
 					defer res.Body.Close()
+					validResponse := bytes.Contains(bodyBytes, []byte(`"status":"success"`))
 					if res.StatusCode >= 200 && res.StatusCode < 300 {
 						if validResponse {
 							s1.Verified = true
@@ -67,7 +62,6 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 							s1.Verified = false
 						}
 					} 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.
 						if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 							continue
 						}

pkg/detectors/auth0managementapitoken/auth0managementapitoken.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,36 +13,28 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
 	client = common.SaneHttpClient()
 
-	// long jwt token but note this is default 8640000 seconds = 24 hours but could be set to maximum 2592000 seconds = 720 hours = 30 days
-	// at https://manage.auth0.com/dashboard/us/dev-63memjo3/apis/management/explorer
 	managementApiTokenPat = regexp.MustCompile(detectors.PrefixRegex([]string{"auth0"}) + `\b(ey[a-zA-Z0-9._-]+)\b`)
-	domainPat             = regexp.MustCompile(`([a-zA-Z0-9\-]{2,16}\.[a-zA-Z0-9_-]{2,3}\.auth0\.com)`) // could be part of url
+	domainPat             = regexp.MustCompile(`([a-zA-Z0-9\-]{2,16}\.[a-zA-Z0-9_-]{2,3}\.auth0\.com)`)
 )
 
-// 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{"auth0"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("auth0")}
 }
 
-// FromData will find and optionally verify Auth0ManagementApiToken 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)
-
-	managementApiTokenMatches := managementApiTokenPat.FindAllStringSubmatch(dataStr, -1)
-	domainMatches := domainPat.FindAllStringSubmatch(dataStr, -1)
+	managementApiTokenMatches := managementApiTokenPat.FindAllSubmatch(data, -1)
+	domainMatches := domainPat.FindAllSubmatch(data, -1)
 
 	for _, managementApiTokenMatch := range managementApiTokenMatches {
 		if len(managementApiTokenMatch) != 2 {
 			continue
 		}
-		managementApiTokenRes := strings.TrimSpace(managementApiTokenMatch[1])
+		managementApiTokenRes := managementApiTokenMatch[1]
 		if len(managementApiTokenRes) < 2000 || len(managementApiTokenRes) > 5000 {
 			continue
 		}
@@ -52,25 +43,22 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			if len(domainMatch) != 2 {
 				continue
 			}
-			domainRes := strings.TrimSpace(domainMatch[1])
+
+			domainRes := domainMatch[1]
 
 			s1 := detectors.Result{
 				DetectorType: detectorspb.DetectorType_Auth0ManagementApiToken,
-				Redacted:     domainRes,
-				Raw:          []byte(managementApiTokenRes),
-				RawV2:        []byte(managementApiTokenRes + domainRes),
+				Redacted:     string(domainRes),
+				Raw:          managementApiTokenRes,
+				RawV2:        append(managementApiTokenRes, domainRes...),
 			}
 
 			if verify {
-				/*
-				   curl -H "Authorization: Bearer $token" https://domain/api/v2/users
-				*/
-
-				req, err := http.NewRequestWithContext(ctx, "GET", "https://"+domainRes+"/api/v2/users", nil)
+				req, err := http.NewRequestWithContext(ctx, "GET", "https://"+string(domainRes)+"/api/v2/users", nil)
 				if err != nil {
 					continue
 				}
-				req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", managementApiTokenRes))
+				req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", string(managementApiTokenRes)))
 				res, err := client.Do(req)
 				if err == nil {
 					defer res.Body.Close()

pkg/detectors/auth0oauth/auth0oauth.go

@@ -1,6 +1,7 @@
 package auth0oauth
 
 import (
+	"bytes"
 	"context"
 	"io"
 	"net/http"
@@ -15,7 +16,6 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
@@ -23,64 +23,54 @@ var (
 
 	clientIdPat     = regexp.MustCompile(detectors.PrefixRegex([]string{"auth0"}) + `\b([a-zA-Z0-9_-]{32,60})\b`)
 	clientSecretPat = regexp.MustCompile(`\b([a-zA-Z0-9_-]{64,})\b`)
-	domainPat       = regexp.MustCompile(`\b([a-zA-Z0-9][a-zA-Z0-9._-]*auth0\.com)\b`) // could be part of url
+	domainPat       = regexp.MustCompile(`\b([a-zA-Z0-9][a-zA-Z0-9._-]*auth0\.com)\b`)
 )
 
-// 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{"auth0"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("auth0")}
 }
 
-// FromData will find and optionally verify Auth0oauth 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)
 
-	clientIdMatches := clientIdPat.FindAllStringSubmatch(dataStr, -1)
-	clientSecretMatches := clientSecretPat.FindAllStringSubmatch(dataStr, -1)
-	domainMatches := domainPat.FindAllStringSubmatch(dataStr, -1)
+	clientIdMatches := clientIdPat.FindAllSubmatch(data, -1)
+	clientSecretMatches := clientSecretPat.FindAllSubmatch(data, -1)
+	domainMatches := domainPat.FindAllSubmatch(data, -1)
 
 	for _, clientIdMatch := range clientIdMatches {
 		if len(clientIdMatch) != 2 {
 			continue
 		}
-		clientIdRes := strings.TrimSpace(clientIdMatch[1])
+		clientIdRes := bytes.TrimSpace(clientIdMatch[1])
 
 		for _, clientSecretMatch := range clientSecretMatches {
 			if len(clientSecretMatch) != 2 {
 				continue
 			}
-			clientSecretRes := strings.TrimSpace(clientSecretMatch[1])
+			clientSecretRes := bytes.TrimSpace(clientSecretMatch[1])
 
 			for _, domainMatch := range domainMatches {
 				if len(domainMatch) != 2 {
 					continue
 				}
-				domainRes := strings.TrimSpace(domainMatch[1])
+				domainRes := bytes.TrimSpace(domainMatch[1])
 
 				s1 := detectors.Result{
 					DetectorType: detectorspb.DetectorType_Auth0oauth,
-					Redacted:     clientIdRes,
-					Raw:          []byte(clientSecretRes),
-					RawV2:        []byte(clientIdRes + clientSecretRes),
+					Redacted:     string(clientIdRes),
+					Raw:          clientSecretRes,
+					RawV2:        append(clientIdRes, clientSecretRes...),
 				}
 
 				if verify {
-					/*
-					   curl --request POST \
-					     --url 'https://YOUR_DOMAIN/oauth/token' \
-					     --header 'content-type: application/x-www-form-urlencoded' \
-					     --data 'grant_type=authorization_code&client_id=W44JmL3qD6LxHeEJyKe9lMuhcwvPOaOq&client_secret=YOUR_CLIENT_SECRET&code=AUTHORIZATION_CODE&redirect_uri=undefined'
-					*/
 
 					data := url.Values{}
 					data.Set("grant_type", "authorization_code")
-					data.Set("client_id", clientIdRes)
-					data.Set("client_secret", clientSecretRes)
+					data.Set("client_id", string(clientIdRes))
+					data.Set("client_secret", string(clientSecretRes))
 					data.Set("code", "AUTHORIZATION_CODE")
 					data.Set("redirect_uri", "undefined")
 
-					req, err := http.NewRequestWithContext(ctx, http.MethodPost, "https://"+domainRes+"/oauth/token", strings.NewReader(data.Encode())) // URL-encoded payload
+					req, err := http.NewRequestWithContext(ctx, http.MethodPost, "https://"+string(domainRes)+"/oauth/token", strings.NewReader(data.Encode()))
 					if err != nil {
 						continue
 					}
@@ -94,11 +84,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 						}
 						body := string(bodyBytes)
 
-						// if client_id and client_secret is valid -> 403 {"error":"invalid_grant","error_description":"Invalid authorization code"}
-						// if invalid -> 401 {"error":"access_denied","error_description":"Unauthorized"}
-						// ingenious!
-
-						if !strings.Contains(body, "access_denied") {
+						if !bytes.Contains(bodyBytes, []byte("access_denied")) {
 							s1.Verified = true
 						} else {
 							if detectors.IsKnownFalsePositive(clientIdRes, detectors.DefaultFalsePositives, true) {

pkg/detectors/autodesk/autodesk.go

@@ -1,11 +1,11 @@
 package autodesk
 
 import (
+	"bytes"
 	"context"
 	"fmt"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,49 +14,41 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
-	client = common.SaneHttpClient()
-
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
+	client    = common.SaneHttpClient()
 	keyPat    = regexp.MustCompile(detectors.PrefixRegex([]string{"autodesk"}) + `\b([0-9A-Za-z]{32})\b`)
 	secretPat = regexp.MustCompile(detectors.PrefixRegex([]string{"autodesk"}) + `\b([0-9A-Za-z]{16})\b`)
 )
 
-// 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{"autodesk"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("autodesk")}
 }
 
-// FromData will find and optionally verify Autodesk 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
-	secretMatches := secretPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
+	secretMatches := secretPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 		for _, secretMatch := range secretMatches {
 			if len(secretMatch) != 2 {
 				continue
 			}
-			resSecret := strings.TrimSpace(secretMatch[1])
+			resSecret := bytes.TrimSpace(secretMatch[1])
 
 			s1 := detectors.Result{
 				DetectorType: detectorspb.DetectorType_Autodesk,
-				Raw:          []byte(resMatch),
-				RawV2:        []byte(resMatch + resSecret),
+				Raw:          resMatch,
+				RawV2:        append(resMatch, resSecret...),
 			}
 
 			if verify {
-				payload := strings.NewReader(fmt.Sprintf(`grant_type=client_credentials&client_id=%s&client_secret=%s`, resMatch, resSecret))
+				payload := bytes.NewReader([]byte(fmt.Sprintf(`grant_type=client_credentials&client_id=%s&client_secret=%s`, string(resMatch), string(resSecret))))
 				req, err := http.NewRequestWithContext(ctx, "POST", "https://developer.api.autodesk.com/authentication/v1/authenticate", payload)
 				if err != nil {
 					continue
@@ -68,7 +60,6 @@ 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.
 						if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 							continue
 						}

pkg/detectors/autoklose/autoklose.go

@@ -1,13 +1,13 @@
 package autoklose
 
 import (
+	"bytes"
 	"context"
 	"encoding/json"
 	"fmt"
 	"io"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -16,41 +16,34 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
 	client = common.SaneHttpClient()
 
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"autoklose"}) + `\b([a-zA-Z0-9-]{32})\b`)
 )
 
-// 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{"autoklose"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("autoklose")}
 }
 
-// FromData will find and optionally verify Autoklose 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_Autoklose,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
-			req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.autoklose.com/api/campaigns/?api_token=%s", resMatch), nil)
+			req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.autoklose.com/api/campaigns/?api_token=%s", string(resMatch)), nil)
 			if err != nil {
 				continue
 			}
@@ -68,7 +61,6 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 						s1.Verified = false
 					}
 				} 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.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/autopilot/autopilot.go

@@ -1,10 +1,10 @@
 package autopilot
 
 import (
+	"bytes"
 	"context"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -13,37 +13,30 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
 	client = common.SaneHttpClient()
 
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"autopilot"}) + `\b([0-9a-f]{32})\b`)
 )
 
-// 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{"autopilot"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("autopilot")}
 }
 
-// FromData will find and optionally verify AutoPilot 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_AutoPilot,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
@@ -51,14 +44,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			if err != nil {
 				continue
 			}
-			req.Header.Add("autopilotapikey", resMatch)
+			req.Header.Add("autopilotapikey", string(resMatch))
 			res, err := client.Do(req)
 			if err == nil {
 				defer res.Body.Close()
 				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.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/avazapersonalaccesstoken/avazapersonalaccesstoken.go

@@ -1,11 +1,11 @@
 package avazapersonalaccesstoken
 
 import (
+	"bytes"
 	"context"
 	"fmt"
 	"net/http"
 	"regexp"
-	"strings"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,53 +14,43 @@ import (
 
 type Scanner struct{}
 
-// Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 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.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"avaza"}) + `\b([0-9]+-[0-9a-f]{40})\b`)
 )
 
-// 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{"avaza"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("avaza")}
 }
 
-// FromData will find and optionally verify AvazaPersonalAccessToken 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_AvazaPersonalAccessToken,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
-			req, err := http.NewRequest("GET", "https://api.avaza.com/api/Account", nil)
+			req, err := http.NewRequestWithContext(ctx, "GET", "https://api.avaza.com/api/Account", nil)
 			if err != nil {
 				continue
 			}
-			req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", resMatch))
+			req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", string(resMatch)))
 			res, err := client.Do(req)
 			if err == nil {
 				defer res.Body.Close()
 				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.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/aviationstack/aviationstack.go

@@ -1,12 +1,11 @@
 package aviationstack
 
 import (
+	"bytes"
 	"context"
 	"fmt"
 	"net/http"
 	"regexp"
-	"strings"
-	"time"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -21,37 +20,31 @@ var _ detectors.Detector = (*Scanner)(nil)
 var (
 	client = common.SaneHttpClient()
 
-	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"aviationstack"}) + `\b([a-z0-9]{32})\b`)
 )
 
 // 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{"aviationstack"}
+func (s Scanner) Keywords() [][]byte {
+	return [][]byte{[]byte("aviationstack")}
 }
 
 // FromData will find and optionally verify AviationStack 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)
-
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	matches := keyPat.FindAllSubmatch(data, -1)
 
 	for _, match := range matches {
 		if len(match) != 2 {
 			continue
 		}
-		resMatch := strings.TrimSpace(match[1])
+		resMatch := bytes.TrimSpace(match[1])
 
 		s1 := detectors.Result{
 			DetectorType: detectorspb.DetectorType_AviationStack,
-			Raw:          []byte(resMatch),
+			Raw:          resMatch,
 		}
 
 		if verify {
-			timeout := 10 * time.Second
-			client.Timeout = timeout
-			req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.aviationstack.com/v1/flights?access_key=%s", resMatch), nil)
+			req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.aviationstack.com/v1/flights?access_key=%s", string(resMatch)), nil)
 			if err != nil {
 				continue
 			}
@@ -61,7 +54,6 @@ 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.
 					if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 						continue
 					}

pkg/detectors/aws/aws.go

@@ -1,6 +1,7 @@
 package aws
 
 import (
+	"bytes"
 	"context"
 	"crypto/hmac"
 	"crypto/sha256"
@@ -19,7 +20,8 @@ import (
 
 type scanner struct {
 	verificationClient *http.Client
-	skipIDs            map[string]struct{}
+
+	skipIDs map[string]struct{}
 }
 
 func New(opts ...func(*scanner)) *scanner {
@@ -61,14 +63,13 @@ var (
 	falsePositiveSecretCheck = regexp.MustCompile(`[a-f0-9]{40}`)
 )
 
-// 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{
-		"AKIA",
-		"ABIA",
-		"ACCA",
-		"ASIA",
+// Returning the keywords as byte arrays
+func (s scanner) Keywords() [][]byte {
+	return [][]byte{
+		[]byte("AKIA"),
+		[]byte("ABIA"),
+		[]byte("ACCA"),
+		[]byte("ASIA"),
 	}
 }
 
@@ -87,19 +88,17 @@ 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) {
-	dataStr := string(data)
-
-	idMatches := idPat.FindAllStringSubmatch(dataStr, -1)
-	secretMatches := secretPat.FindAllStringSubmatch(dataStr, -1)
+	idMatches := idPat.FindAllSubmatch(data, -1)
+	secretMatches := secretPat.FindAllSubmatch(data, -1)
 
 	for _, idMatch := range idMatches {
 		if len(idMatch) != 2 {
 			continue
 		}
-		resIDMatch := strings.TrimSpace(idMatch[1])
+		resIDMatch := bytes.TrimSpace(idMatch[1])
 
 		if s.skipIDs != nil {
-			if _, ok := s.skipIDs[resIDMatch]; ok {
+			if _, ok := s.skipIDs[string(resIDMatch)]; ok {
 				continue
 			}
 		}
@@ -108,13 +107,13 @@ func (s scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			if len(secretMatch) != 2 {
 				continue
 			}
-			resSecretMatch := strings.TrimSpace(secretMatch[1])
+			resSecretMatch := bytes.TrimSpace(secretMatch[1])
 
 			s1 := detectors.Result{
 				DetectorType: detectorspb.DetectorType_AWS,
-				Raw:          []byte(resIDMatch),
-				Redacted:     resIDMatch,
-				RawV2:        []byte(resIDMatch + resSecretMatch),
+				Raw:          resIDMatch,
+				Redacted:     string(resIDMatch),
+				RawV2:        append(append([]byte(nil), resIDMatch...), resSecretMatch...),
 			}
 
 			if verify {
@@ -146,17 +145,17 @@ func (s scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 				params.Add("Action", "GetCallerIdentity")
 				params.Add("Version", "2011-06-15")
 				params.Add("X-Amz-Algorithm", algorithm)
-				params.Add("X-Amz-Credential", resIDMatch+"/"+credentialScope)
+				params.Add("X-Amz-Credential", string(resIDMatch)+"/"+credentialScope)
 				params.Add("X-Amz-Date", amzDate)
 				params.Add("X-Amz-Expires", "30")
 				params.Add("X-Amz-SignedHeaders", signedHeaders)
 
 				canonicalQuerystring := params.Encode()
 				payloadHash := GetHash("") // empty payload
-				canonicalRequest := method + "\n" + canonicalURI + "\n" + canonicalQuerystring + "\n" + canonicalHeaders + "\n" + signedHeaders + "\n" + payloadHash
+				canonicalRequest := string(method) + "\n" + string(canonicalURI) + "\n" + string(canonicalQuerystring) + "\n" + string(canonicalHeaders) + "\n" + string(signedHeaders) + "\n" + string(payloadHash)
 
 				// TASK 2: CREATE THE STRING TO SIGN.
-				stringToSign := algorithm + "\n" + amzDate + "\n" + credentialScope + "\n" + GetHash(canonicalRequest)
+				stringToSign := string(algorithm) + "\n" + string(amzDate) + "\n" + string(credentialScope) + "\n" + string(GetHash(canonicalRequest))
 
 				// TASK 3: CALCULATE THE SIGNATURE.
 				// https://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html
@@ -228,7 +227,7 @@ func (s scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			}
 
 			// If the result is unverified and matches something like a git hash, don't include it in the results.
-			if !s1.Verified && falsePositiveSecretCheck.MatchString(resSecretMatch) {
+			if !s1.Verified && falsePositiveSecretCheck.Match(resSecretMatch) {
 				continue
 			}
 
@@ -242,6 +241,157 @@ func (s scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 	return awsCustomCleanResults(results), nil
 }
 
+// func (s scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
+// 	idMatches := idPat.FindAllSubmatch(data, -1)
+// 	secretMatches := secretPat.FindAllSubmatch(data, -1)
+//
+// 	for _, idMatch := range idMatches {
+// 		if len(idMatch) != 2 {
+// 			continue
+// 		}
+// 		resIDMatch := bytes.TrimSpace(idMatch[1])
+//
+// 		if s.skipIDs != nil {
+// 			if _, ok := s.skipIDs[string(resIDMatch)]; ok {
+// 				continue
+// 			}
+// 		}
+//
+// 		for _, secretMatch := range secretMatches {
+// 			if len(secretMatch) != 2 {
+// 				continue
+// 			}
+// 			resSecretMatch := bytes.TrimSpace(secretMatch[1])
+//
+// 			s1 := detectors.Result{
+// 				DetectorType: detectorspb.DetectorType_AWS,
+// 				Raw:          resIDMatch,
+// 				Redacted:     string(resIDMatch),
+// 				RawV2:        append(append([]byte(nil), resIDMatch...), resSecretMatch...),
+// 			}
+//
+// 			if verify {
+// 				// Each string operation is converted into byte operations
+//
+// 				method := []byte("GET")
+// 				service := []byte("sts")
+// 				host := []byte("sts.amazonaws.com")
+// 				region := []byte("us-east-1")
+// 				endpoint := []byte("https://sts.amazonaws.com")
+// 				datestamp := []byte(time.Now().UTC().Format("20060102"))
+// 				amzDate := []byte(time.Now().UTC().Format("20060102T150405Z0700"))
+//
+// 				req, err := http.NewRequestWithContext(ctx, string(method), string(endpoint), nil)
+// 				if err != nil {
+// 					continue
+// 				}
+// 				req.Header.Set("Accept", "application/json")
+//
+// 				// Byte operations for the subsequent string operations
+//
+// 				canonicalURI := []byte("/")
+// 				canonicalHeaders := []byte("host:" + string(host) + "\n")
+// 				signedHeaders := []byte("host")
+// 				algorithm := []byte("AWS4-HMAC-SHA256")
+// 				credentialScope := []byte(fmt.Sprintf("%s/%s/%s/aws4_request", datestamp, region, service))
+//
+// 				params := req.URL.Query()
+// 				params.Add("Action", "GetCallerIdentity")
+// 				params.Add("Version", "2011-06-15")
+// 				params.Add("X-Amz-Algorithm", string(algorithm))
+// 				params.Add("X-Amz-Credential", string(resIDMatch)+"/"+string(credentialScope))
+// 				params.Add("X-Amz-Date", string(amzDate))
+// 				params.Add("X-Amz-Expires", "30")
+// 				params.Add("X-Amz-SignedHeaders", string(signedHeaders))
+//
+// 				canonicalQuerystring := params.Encode()
+// 				payloadHash := GetHash([]byte("")) // empty payload
+// 				canonicalRequest := string(method) + "\n" + string(canonicalURI) + "\n" + string(canonicalQuerystring) + "\n" + string(canonicalHeaders) + "\n" + string(signedHeaders) + "\n" + string(payloadHash)
+//
+// 				// TASK 2: CREATE THE STRING TO SIGN.
+// 				stringToSign := string(algorithm) + "\n" + string(amzDate) + "\n" + string(credentialScope) + "\n" + string(GetHash([]byte(canonicalRequest)))
+//
+// 				hash := GetHMAC([]byte(fmt.Sprintf("AWS4%s", string(resSecretMatch))), datestamp)
+// 				hash = GetHMAC(hash, region)
+// 				hash = GetHMAC(hash, service)
+// 				hash = GetHMAC(hash, []byte("aws4_request"))
+//
+// 				signature2 := GetHMAC(hash, []byte(stringToSign)) // Get Signature HMAC SHA256
+// 				signature := hex.EncodeToString(signature2)
+//
+// 				params.Add("X-Amz-Signature", signature)
+// 				req.Header.Add("Content-type", "application/x-www-form-urlencoded; charset=utf-8")
+// 				req.URL.RawQuery = params.Encode()
+//
+// 				client := s.verificationClient
+// 				if client == nil {
+// 					client = defaultVerificationClient
+// 				}
+// 				res, err := client.Do(req)
+// 				if err == nil {
+//
+// 					if res.StatusCode >= 200 && res.StatusCode < 300 {
+// 						identityInfo := identityRes{}
+// 						err := json.NewDecoder(res.Body).Decode(&identityInfo)
+// 						if err == nil {
+// 							s1.Verified = true
+// 							s1.ExtraData = map[string]string{
+// 								"account": identityInfo.GetCallerIdentityResponse.GetCallerIdentityResult.Account,
+// 								"user_id": identityInfo.GetCallerIdentityResponse.GetCallerIdentityResult.UserID,
+// 								"arn":     identityInfo.GetCallerIdentityResponse.GetCallerIdentityResult.Arn,
+// 							}
+// 						} else {
+// 							s1.VerificationError = err
+// 						}
+// 						res.Body.Close()
+// 					} 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.
+// 						if detectors.IsKnownFalsePositive(resSecretMatch, detectors.DefaultFalsePositives, true) {
+// 							continue
+// 						}
+//
+// 						if res.StatusCode == 403 {
+// 							var body awsErrorResponseBody
+// 							err = json.NewDecoder(res.Body).Decode(&body)
+// 							res.Body.Close()
+// 							if err == nil {
+// 								// All instances of the code I've seen in the wild are PascalCased but this check is
+// 								// case-insensitive out of an abundance of caution
+// 								if strings.EqualFold(body.Error.Code, "InvalidClientTokenId") {
+// 									// determinate failure - nothing to do
+// 								} else {
+// 									// We see a surprising number of false-negative signature mismatch errors here
+// 									// (The official SDK somehow elicits even more than just making the request
+// 									// ourselves)
+// 									s1.VerificationError = fmt.Errorf("request to %v returned status %d with an unexpected reason (%s: %s)", res.Request.URL, res.StatusCode, body.Error.Code, body.Error.Message)
+// 								}
+// 							} else {
+// 								s1.VerificationError = fmt.Errorf("couldn't parse the sts response body (%v)", err)
+// 							}
+// 						} else {
+// 							s1.VerificationError = fmt.Errorf("request to %v returned unexpected status %d", res.Request.URL, res.StatusCode)
+// 						}
+// 					}
+// 				} else {
+// 					s1.VerificationError = err
+// 				}
+// 			}
+//
+// 			// If the result is unverified and matches something like a git hash, don't include it in the results.
+// 			if !s1.Verified && falsePositiveSecretCheck.Match(resSecretMatch) {
+// 				continue
+// 			}
+//
+// 			results = append(results, s1)
+// 			// If we've found a verified match with this ID, we don't need to look for any more. So move on to the next ID.
+// 			if s1.Verified {
+// 				break
+// 			}
+// 		}
+// 	}
+// 	return awsCustomCleanResults(results), nil
+// }
+
 func awsCustomCleanResults(results []detectors.Result) []detectors.Result {
 	if len(results) == 0 {
 		return results

pkg/detectors/salesforce/salesforce.go

@@ -43,6 +43,8 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 	instanceMatches := instancePat.FindAllStringSubmatch(dataStr, -1)
 	tokenMatches := accessTokenPat.FindAllStringSubmatch(dataStr, -1)
 
+	fmt.Printf("instanceMatches: %v\n", instanceMatches)
+
 	for _, instance := range instanceMatches {
 		if len(instance) != 1 {
 			continue

pkg/engine/defaults.go

@@ -2,10 +2,6 @@ package engine
 
 import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/envoyapikey"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/huggingface"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/salesforce"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/snowflake"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/trufflehogenterprise"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/abbysale"
@@ -291,7 +287,6 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/getresponse"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/getsandbox"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/github"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/github_oauth2"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/github_old"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/githubapp"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/gitlab"
@@ -561,6 +556,7 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/satismeterwritekey"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/saucelabs"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/scalewaykey"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/github_oauth2"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/scalr"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/scrapeowl"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/scraperapi"
@@ -1536,10 +1532,6 @@ func DefaultDetectors() []detectors.Detector {
 		couchbase.Scanner{},
 		envoyapikey.Scanner{},
 		github_oauth2.Scanner{},
-		snowflake.Scanner{},
-		huggingface.Scanner{},
-		trufflehogenterprise.Scanner{},
-		salesforce.Scanner{},
 	}
 
 }

pkg/handlers/archive.go

@@ -29,8 +29,6 @@ var (
 	maxDepth   = 5
 	maxSize    = 250 * 1024 * 1024 // 20MB
 	maxTimeout = time.Duration(30) * time.Second
-
-	defaultBufferSize = 512
 )
 
 // Ensure the Archive satisfies the interfaces at compile time.
@@ -64,7 +62,7 @@ func SetArchiveMaxTimeout(timeout time.Duration) {
 
 // FromFile extracts the files from an archive.
 func (a *Archive) FromFile(originalCtx context.Context, data io.Reader) chan []byte {
-	archiveChan := make(chan []byte, defaultBufferSize)
+	archiveChan := make(chan []byte, 512)
 	go func() {
 		ctx, cancel := context.WithTimeout(originalCtx, maxTimeout)
 		logger := logContext.AddLogger(ctx).Logger()
@@ -185,28 +183,29 @@ func (a *Archive) ReadToMax(ctx context.Context, reader io.Reader) (data []byte,
 			logger.Error(err, "Panic occurred when reading archive")
 		}
 	}()
-
-	if common.IsDone(ctx) {
-		return nil, ctx.Err()
+	fileContent := bytes.Buffer{}
+	logger.V(5).Info("Remaining buffer capacity", "bytes", maxSize-a.size)
+	for i := 0; i <= maxSize/512; i++ {
+		if common.IsDone(ctx) {
+			return nil, ctx.Err()
+		}
+		fileChunk := make([]byte, 512)
+		bRead, err := reader.Read(fileChunk)
+		if err != nil && !errors.Is(err, io.EOF) {
+			return []byte{}, err
+		}
+		a.size += bRead
+		if len(fileChunk) > 0 {
+			fileContent.Write(fileChunk[0:bRead])
+		}
+		if bRead < 512 {
+			return fileContent.Bytes(), nil
+		}
+		if a.size >= maxSize && bRead == 512 {
+			logger.V(2).Info("Max archive size reached.")
+			return fileContent.Bytes(), nil
+		}
 	}
-
-	var fileContent bytes.Buffer
-	// Create a limited reader to ensure we don't read more than the max size.
-	lr := io.LimitReader(reader, int64(maxSize))
-
-	// Using io.CopyBuffer for performance advantages. Though buf is mandatory
-	// for the method, due to the internal implementation of io.CopyBuffer, when
-	// *bytes.Buffer implements io.WriterTo or io.ReaderFrom, the provided buf
-	// is simply ignored. Thus, we can pass nil for the buf parameter.
-	_, err = io.CopyBuffer(&fileContent, lr, nil)
-	if err != nil && !errors.Is(err, io.EOF) {
-		return nil, err
-	}
-
-	if fileContent.Len() == maxSize {
-		logger.V(2).Info("Max archive size reached.")
-	}
-
 	return fileContent.Bytes(), nil
 }
 

pkg/handlers/archive_test.go

@@ -1,7 +1,6 @@
 package handlers
 
 import (
-	"bytes"
 	"context"
 	"io"
 	"net/http"
@@ -127,58 +126,6 @@ func TestHandleFile(t *testing.T) {
 	assert.Equal(t, 1, len(ch))
 }
 
-func TestReadToMax(t *testing.T) {
-	tests := []struct {
-		name     string
-		input    []byte
-		expected []byte
-	}{
-		{
-			name:     "read full content within maxSize",
-			input:    []byte("abcdefg"),
-			expected: []byte("abcdefg"),
-		},
-		{
-			name:     "read content larger than maxSize",
-			input:    make([]byte, maxSize+10), // this creates a byte slice 10 bytes larger than maxSize
-			expected: make([]byte, maxSize),
-		},
-		{
-			name:     "empty input",
-			input:    []byte(""),
-			expected: []byte(""),
-		},
-	}
-
-	a := &Archive{}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			reader := bytes.NewReader(tt.input)
-			output, err := a.ReadToMax(context.Background(), reader)
-			assert.Nil(t, err)
-
-			assert.Equal(t, tt.expected, output)
-		})
-	}
-}
-
-func BenchmarkReadToMax(b *testing.B) {
-	data := bytes.Repeat([]byte("a"), 1024*1000) // 1MB of data.
-	reader := bytes.NewReader(data)
-	a := &Archive{}
-
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		b.StartTimer()
-		_, _ = a.ReadToMax(context.Background(), reader)
-		b.StopTimer()
-
-		_, _ = reader.Seek(0, 0) // Reset the reader position.
-		a.size = 0               // Reset archive size.
-	}
-}
-
 func TestExtractDebContent(t *testing.T) {
 	// Open the sample .deb file from the testdata folder.
 	file, err := os.Open("testdata/test.deb")

pkg/output/legacy_json.go

@@ -133,7 +133,7 @@ func BranchHeads(repo *gogit.Repository) (map[string]*object.Commit, error) {
 		}
 		headCommit, err := repo.CommitObject(*headHash)
 		if err != nil {
-			logger.Error(err, "unable to get commit", "head_hash", headHash.String())
+			logger.Error(err, "unable to get commit", "commit", headCommit.String())
 			return nil
 		}
 		branches[branchName] = headCommit

pkg/sources/chunker.go

@@ -20,7 +20,7 @@ const (
 
 // Chunker takes a chunk and splits it into chunks of ChunkSize.
 func Chunker(originalChunk *Chunk) chan *Chunk {
-	chunkChan := make(chan *Chunk, 1)
+	chunkChan := make(chan *Chunk)
 	go func() {
 		defer close(chunkChan)
 		if len(originalChunk.Data) <= TotalChunkSize {

pkg/sources/circleci/circleci.go

@@ -238,7 +238,6 @@ func (s *Source) chunkAction(ctx context.Context, proj project, bld build, act a
 			SourceType: s.Type(),
 			SourceName: s.name,
 			SourceID:   s.SourceID(),
-			JobID:      s.JobID(),
 			Data:       removeCircleSha1Line(data.Bytes()),
 			SourceMetadata: &source_metadatapb.MetaData{
 				Data: &source_metadatapb.MetaData_Circleci{

pkg/sources/docker/docker.go

@@ -174,7 +174,6 @@ func (s *Source) Chunks(ctx context.Context, chunksChan chan *sources.Chunk) err
 					SourceType: s.Type(),
 					SourceName: s.name,
 					SourceID:   s.SourceID(),
-					JobID:      s.JobID(),
 					Data:       file.Bytes(),
 					SourceMetadata: &source_metadatapb.MetaData{
 						Data: &source_metadatapb.MetaData_Docker{

pkg/sources/filesystem/filesystem.go

@@ -161,7 +161,6 @@ func (s *Source) scanFile(ctx context.Context, path string, chunksChan chan *sou
 		SourceType: s.Type(),
 		SourceName: s.name,
 		SourceID:   s.SourceID(),
-		JobID:      s.JobID(),
 		SourceMetadata: &source_metadatapb.MetaData{
 			Data: &source_metadatapb.MetaData_Filesystem{
 				Filesystem: &source_metadatapb.Filesystem{
@@ -192,7 +191,6 @@ func (s *Source) scanFile(ctx context.Context, path string, chunksChan chan *sou
 			SourceType: s.Type(),
 			SourceName: s.name,
 			SourceID:   s.SourceID(),
-			JobID:      s.JobID(),
 			Data:       data.Bytes(),
 			SourceMetadata: &source_metadatapb.MetaData{
 				Data: &source_metadatapb.MetaData_Filesystem{

pkg/sources/gcs/gcs.go

@@ -324,7 +324,6 @@ func (s *Source) processObject(ctx context.Context, o object) error {
 	chunkSkel := &sources.Chunk{
 		SourceName: s.name,
 		SourceType: s.Type(),
-		JobID:      s.JobID(),
 		SourceID:   s.sourceId,
 		Verify:     s.verify,
 		SourceMetadata: &source_metadatapb.MetaData{

pkg/sources/git/git.go

@@ -446,7 +446,6 @@ func (s *Git) ScanCommits(ctx context.Context, repo *git.Repository, path string
 				chunkSkel := &sources.Chunk{
 					SourceName:     s.sourceName,
 					SourceID:       s.sourceID,
-					JobID:          s.jobID,
 					SourceType:     s.sourceType,
 					SourceMetadata: metadata,
 					Verify:         s.verify,
@@ -465,7 +464,6 @@ func (s *Git) ScanCommits(ctx context.Context, repo *git.Repository, path string
 			chunksChan <- &sources.Chunk{
 				SourceName:     s.sourceName,
 				SourceID:       s.sourceID,
-				JobID:          s.jobID,
 				SourceType:     s.sourceType,
 				SourceMetadata: metadata,
 				Data:           diff.Content.Bytes(),
@@ -492,7 +490,6 @@ func (s *Git) gitChunk(ctx context.Context, diff gitparse.Diff, fileName, email,
 				chunksChan <- &sources.Chunk{
 					SourceName:     s.sourceName,
 					SourceID:       s.sourceID,
-					JobID:          s.jobID,
 					SourceType:     s.sourceType,
 					SourceMetadata: metadata,
 					Data:           append([]byte{}, newChunkBuffer.Bytes()...),
@@ -507,7 +504,6 @@ func (s *Git) gitChunk(ctx context.Context, diff gitparse.Diff, fileName, email,
 				chunksChan <- &sources.Chunk{
 					SourceName:     s.sourceName,
 					SourceID:       s.sourceID,
-					JobID:          s.jobID,
 					SourceType:     s.sourceType,
 					SourceMetadata: metadata,
 					Data:           line,
@@ -527,7 +523,6 @@ func (s *Git) gitChunk(ctx context.Context, diff gitparse.Diff, fileName, email,
 		chunksChan <- &sources.Chunk{
 			SourceName:     s.sourceName,
 			SourceID:       s.sourceID,
-			JobID:          s.jobID,
 			SourceType:     s.sourceType,
 			SourceMetadata: metadata,
 			Data:           append([]byte{}, newChunkBuffer.Bytes()...),
@@ -593,7 +588,6 @@ func (s *Git) ScanStaged(ctx context.Context, repo *git.Repository, path string,
 				chunkSkel := &sources.Chunk{
 					SourceName:     s.sourceName,
 					SourceID:       s.sourceID,
-					JobID:          s.jobID,
 					SourceType:     s.sourceType,
 					SourceMetadata: metadata,
 					Verify:         s.verify,
@@ -608,7 +602,6 @@ func (s *Git) ScanStaged(ctx context.Context, repo *git.Repository, path string,
 			chunksChan <- &sources.Chunk{
 				SourceName:     s.sourceName,
 				SourceID:       s.sourceID,
-				JobID:          s.jobID,
 				SourceType:     s.sourceType,
 				SourceMetadata: metadata,
 				Data:           diff.Content.Bytes(),

pkg/sources/github/github.go

@@ -149,16 +149,14 @@ func (s *Source) newFilteredRepoCache(c cache.Cache, include, exclude []string)
 	for _, ig := range include {
 		g, err := glob.Compile(ig)
 		if err != nil {
-			s.log.V(1).Info("invalid include glob", "include_value", ig, "err", err)
-			continue
+			s.log.V(1).Info("invalid include glob", "glob", g, "err", err)
 		}
 		includeGlobs = append(includeGlobs, g)
 	}
 	for _, eg := range exclude {
 		g, err := glob.Compile(eg)
 		if err != nil {
-			s.log.V(1).Info("invalid exclude glob", "exclude_value", eg, "err", err)
-			continue
+			s.log.V(1).Info("invalid exclude glob", "glob", g, "err", err)
 		}
 		excludeGlobs = append(excludeGlobs, g)
 	}
@@ -1225,7 +1223,6 @@ func (s *Source) chunkIssueComments(ctx context.Context, repo, repoPath string,
 		chunk := &sources.Chunk{
 			SourceName: s.name,
 			SourceID:   s.SourceID(),
-			JobID:      s.JobID(),
 			SourceType: s.Type(),
 			SourceMetadata: &source_metadatapb.MetaData{
 				Data: &source_metadatapb.MetaData_Github{
@@ -1259,7 +1256,6 @@ func (s *Source) chunkPullRequestComments(ctx context.Context, repo string, comm
 			SourceName: s.name,
 			SourceID:   s.SourceID(),
 			SourceType: s.Type(),
-			JobID:      s.JobID(),
 			SourceMetadata: &source_metadatapb.MetaData{
 				Data: &source_metadatapb.MetaData_Github{
 					Github: &source_metadatapb.Github{
@@ -1291,7 +1287,6 @@ func (s *Source) chunkGistComments(ctx context.Context, gistUrl string, comments
 			SourceName: s.name,
 			SourceID:   s.SourceID(),
 			SourceType: s.Type(),
-			JobID:      s.JobID(),
 			SourceMetadata: &source_metadatapb.MetaData{
 				Data: &source_metadatapb.MetaData_Github{
 					Github: &source_metadatapb.Github{

pkg/sources/s3/s3.go

@@ -376,7 +376,6 @@ func (s *Source) pageChunker(ctx context.Context, client *s3.S3, chunksChan chan
 				SourceType: s.Type(),
 				SourceName: s.name,
 				SourceID:   s.SourceID(),
-				JobID:      s.JobID(),
 				SourceMetadata: &source_metadatapb.MetaData{
 					Data: &source_metadatapb.MetaData_S3{
 						S3: &source_metadatapb.S3{

pkg/sources/source_manager.go

@@ -36,10 +36,7 @@ type SourceManager struct {
 	handles     map[handle]sourceInfo
 	handlesLock sync.Mutex
 	// Pool limiting the amount of concurrent sources running.
-	pool                errgroup.Group
-	poolLimit           int
-	currentRunningCount int32
-	// Max number of units to scan concurrently per source.
+	pool            errgroup.Group
 	concurrentUnits int
 	// Run the sources using source unit enumeration / chunking if available.
 	useSourceUnits bool
@@ -71,10 +68,7 @@ func WithReportHook(hook JobProgressHook) func(*SourceManager) {
 
 // WithConcurrentSources limits the concurrent number of sources a manager can run.
 func WithConcurrentSources(concurrency int) func(*SourceManager) {
-	return func(mgr *SourceManager) {
-		mgr.pool.SetLimit(concurrency)
-		mgr.poolLimit = concurrency
-	}
+	return func(mgr *SourceManager) { mgr.pool.SetLimit(concurrency) }
 }
 
 // WithBufferedOutput sets the size of the buffer used for the Chunks() channel.
@@ -173,8 +167,6 @@ func (s *SourceManager) asyncRun(ctx context.Context, handle handle) (JobProgres
 	ctx, cancel := context.WithCancel(ctx)
 	progress := NewJobProgress(jobID, int64(handle), sourceName, WithHooks(s.hooks...), WithCancel(cancel))
 	s.pool.Go(func() error {
-		atomic.AddInt32(&s.currentRunningCount, 1)
-		defer atomic.AddInt32(&s.currentRunningCount, -1)
 		ctx := context.WithValues(ctx,
 			"job_id", jobID,
 			"source_manager_worker_id", common.RandomID(5),
@@ -215,16 +207,6 @@ func (s *SourceManager) ScanChunk(chunk *Chunk) {
 	s.outputChunks <- chunk
 }
 
-// AvailableCapacity returns the number of concurrent jobs the manager can
-// accommodate at this time. If there is no limit, -1 is returned.
-func (s *SourceManager) AvailableCapacity() int {
-	if s.poolLimit == 0 {
-		return -1
-	}
-	runCount := atomic.LoadInt32(&s.currentRunningCount)
-	return s.poolLimit - int(runCount)
-}
-
 // preflightChecks is a helper method to check the Manager or the context isn't
 // done and that the handle is valid.
 func (s *SourceManager) preflightChecks(ctx context.Context, handle handle) error {

pkg/sources/source_manager_test.go

@@ -317,24 +317,3 @@ func TestSourceManagerCancelRun(t *testing.T) {
 	assert.Error(t, ref.Snapshot().FatalError())
 	assert.True(t, errors.Is(ref.Snapshot().FatalError(), returnedErr))
 }
-
-func TestSourceManagerAvailableCapacity(t *testing.T) {
-	mgr := NewManager(WithConcurrentSources(1337))
-	start, end := make(chan struct{}), make(chan struct{})
-	handle, err := enrollDummy(mgr, callbackChunker{func(context.Context, chan *Chunk) error {
-		start <- struct{}{} // Send start signal.
-		<-end               // Wait for end signal.
-		return nil
-	}})
-	assert.NoError(t, err)
-
-	assert.Equal(t, 1337, mgr.AvailableCapacity())
-	ref, err := mgr.ScheduleRun(context.Background(), handle)
-	assert.NoError(t, err)
-
-	<-start // Wait for start signal.
-	assert.Equal(t, 1336, mgr.AvailableCapacity())
-	end <- struct{}{} // Send end signal.
-	<-ref.Done()      // Wait for the job to finish.
-	assert.Equal(t, 1337, mgr.AvailableCapacity())
-}

pkg/sources/syslog/syslog.go

@@ -272,7 +272,6 @@ func (s *Source) monitorConnection(ctx context.Context, conn net.Conn, chunksCha
 			SourceName:     s.syslog.sourceName,
 			SourceID:       s.syslog.sourceID,
 			SourceType:     s.syslog.sourceType,
-			JobID:          s.JobID(),
 			SourceMetadata: metadata,
 			Data:           input,
 			Verify:         s.verify,
@@ -314,7 +313,6 @@ func (s *Source) acceptUDPConnections(ctx context.Context, netListener net.Packe
 		chunksChan <- &sources.Chunk{
 			SourceName:     s.syslog.sourceName,
 			SourceID:       s.syslog.sourceID,
-			JobID:          s.JobID(),
 			SourceType:     s.syslog.sourceType,
 			SourceMetadata: metadata,
 			Data:           input,