Merge branch 'main' into update/gcpapplicationdefaultcreds-detector

go.mod

@@ -108,7 +108,7 @@ require (
 	golang.org/x/oauth2 v0.23.0
 	golang.org/x/sync v0.8.0
 	golang.org/x/text v0.19.0
-	google.golang.org/api v0.202.0
+	google.golang.org/api v0.203.0
 	google.golang.org/protobuf v1.35.1
 	gopkg.in/h2non/gock.v1 v1.1.2
 	gopkg.in/yaml.v2 v2.4.0
@@ -121,7 +121,7 @@ require (
 require (
 	cel.dev/expr v0.16.1 // indirect
 	cloud.google.com/go v0.116.0 // indirect
-	cloud.google.com/go/auth v0.9.8 // indirect
+	cloud.google.com/go/auth v0.9.9 // indirect
 	cloud.google.com/go/auth/oauth2adapt v0.2.4 // indirect
 	cloud.google.com/go/compute/metadata v0.5.2 // indirect
 	cloud.google.com/go/iam v1.2.1 // indirect

go.sum

@@ -17,6 +17,8 @@ cloud.google.com/go/auth v0.9.5 h1:4CTn43Eynw40aFVr3GpPqsQponx2jv0BQpjvajsbbzw=
 cloud.google.com/go/auth v0.9.5/go.mod h1:Xo0n7n66eHyOWWCnitop6870Ilwo3PiZyodVkkH1xWM=
 cloud.google.com/go/auth v0.9.8 h1:+CSJ0Gw9iVeSENVCKJoLHhdUykDgXSc4Qn+gu2BRtR8=
 cloud.google.com/go/auth v0.9.8/go.mod h1:xxA5AqpDrvS+Gkmo9RqrGGRh6WSNKKOXhY3zNOr38tI=
+cloud.google.com/go/auth v0.9.9 h1:BmtbpNQozo8ZwW2t7QJjnrQtdganSdmqeIBxHxNkEZQ=
+cloud.google.com/go/auth v0.9.9/go.mod h1:xxA5AqpDrvS+Gkmo9RqrGGRh6WSNKKOXhY3zNOr38tI=
 cloud.google.com/go/auth/oauth2adapt v0.2.4 h1:0GWE/FUsXhf6C+jAkWgYm7X9tK8cuEIfy19DBn6B6bY=
 cloud.google.com/go/auth/oauth2adapt v0.2.4/go.mod h1:jC/jOpwFP6JBxhB3P5Rr0a9HLMC/Pe3eaL4NmdvqPtc=
 cloud.google.com/go/bigquery v1.0.1/go.mod h1:i/xbL2UlR5RvWAURpBYZTtm/cXjCha9lbfbpx4poX+o=
@@ -1135,6 +1137,8 @@ google.golang.org/api v0.201.0 h1:+7AD9JNM3tREtawRMu8sOjSbb8VYcYXJG/2eEOmfDu0=
 google.golang.org/api v0.201.0/go.mod h1:HVY0FCHVs89xIW9fzf/pBvOEm+OolHa86G/txFezyq4=
 google.golang.org/api v0.202.0 h1:y1iuVHMqokQbimW79ZqPZWo4CiyFu6HcCYHwSNyzlfo=
 google.golang.org/api v0.202.0/go.mod h1:3Jjeq7M/SFblTNCp7ES2xhq+WvGL0KeXI0joHQBfwTQ=
+google.golang.org/api v0.203.0 h1:SrEeuwU3S11Wlscsn+LA1kb/Y5xT8uggJSkIhD08NAU=
+google.golang.org/api v0.203.0/go.mod h1:BuOVyCSYEPwJb3npWvDnNmFI92f3GeRnHNkETneT3SI=
 google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
 google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
 google.golang.org/appengine v1.5.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=

pkg/detectors/aeroworkflow/aeroworkflow.go

@@ -27,7 +27,7 @@ var (
 	defaultClient = 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{"aeroworkflow"}) + `([a-zA-Z0-9^!?#:*;]{20})\b`)
+	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"aeroworkflow"}) + `\b([a-zA-Z0-9^!?#:*;]{20})`)
 	idPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"aeroworkflow"}) + `\b([0-9]{1,})\b`)
 )
 
@@ -85,7 +85,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 }
 
 func verifyAeroworkflow(ctx context.Context, client *http.Client, resMatch, resIdMatch string) (bool, error) {
-	req, err := http.NewRequestWithContext(ctx, http.MethodGet, aeroworkflowURL+"/api/"+resIdMatch+"/v1/AeroAppointments", nil)
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, aeroworkflowURL+"/api/"+resIdMatch+"/me", nil)
 	if err != nil {
 		return false, err
 	}

pkg/detectors/alegra/alegra.go

@@ -2,6 +2,8 @@ package alegra
 
 import (
 	"context"
+	"fmt"
+	"io"
 	"net/http"
 	"strings"
 
@@ -13,18 +15,17 @@ import (
 )
 
 type Scanner struct {
-	detectors.DefaultMultiPartCredentialProvider
+	client *http.Client
 }
 
 // Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
-	client = common.SaneHttpClient()
-
+	defaultClient = 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{"alegra"}) + `\b([a-z0-9-]{20})\b`)
-	idPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"alegra"}) + `\b([a-zA-Z0-9\.\-\@]{25,30})\b`)
+	idPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"alegra"}) + common.EmailPattern)
 )
 
 // Keywords are used for efficiently pre-filtering chunks.
@@ -37,41 +38,38 @@ func (s Scanner) Keywords() []string {
 func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
 	dataStr := string(data)
 
-	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	keyMatches := keyPat.FindAllStringSubmatch(dataStr, -1)
 	idMatches := idPat.FindAllStringSubmatch(dataStr, -1)
 
-	for _, match := range matches {
-		if len(match) != 2 {
-			continue
-		}
-		tokenPatMatch := strings.TrimSpace(match[1])
+	uniqueTokens := make(map[string]struct{})
+	uniqueIDs := make(map[string]struct{})
 
-		for _, idMatch := range idMatches {
-			if len(idMatch) != 2 {
-				continue
-			}
+	for _, match := range keyMatches {
+		uniqueTokens[match[1]] = struct{}{}
+	}
 
-			userPatMatch := strings.TrimSpace(idMatch[1])
+	for _, match := range idMatches {
+		id := match[0][strings.LastIndex(match[0], " ")+1:]
+		uniqueIDs[id] = struct{}{}
+	}
 
+	for token := range uniqueTokens {
+		for id := range uniqueIDs {
 			s1 := detectors.Result{
 				DetectorType: detectorspb.DetectorType_Alegra,
-				Raw:          []byte(tokenPatMatch),
-				RawV2:        []byte(tokenPatMatch + userPatMatch),
+				Raw:          []byte(token),
+				RawV2:        []byte(token + ":" + id),
 			}
 
 			if verify {
-				req, err := http.NewRequestWithContext(ctx, "GET", "https://api.alegra.com/api/v1/users", nil)
-				if err != nil {
-					continue
-				}
-				req.SetBasicAuth(userPatMatch, tokenPatMatch)
-				res, err := client.Do(req)
-				if err == nil {
-					defer res.Body.Close()
-					if res.StatusCode >= 200 && res.StatusCode < 300 {
-						s1.Verified = true
-					}
+				client := s.client
+				if client == nil {
+					client = defaultClient
 				}
+
+				isVerified, verificationErr := verifyCredentials(ctx, client, id, token)
+				s1.Verified = isVerified
+				s1.SetVerificationError(verificationErr, token)
 			}
 
 			results = append(results, s1)
@@ -81,6 +79,32 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 	return results, nil
 }
 
+func verifyCredentials(ctx context.Context, client *http.Client, username, token string) (bool, error) {
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, "https://api.alegra.com/api/v1/users/self", nil)
+	if err != nil {
+		return false, nil
+	}
+	req.SetBasicAuth(username, token)
+
+	res, err := client.Do(req)
+	if err != nil {
+		return false, err
+	}
+	defer func() {
+		_, _ = io.Copy(io.Discard, res.Body)
+		_ = res.Body.Close()
+	}()
+
+	switch res.StatusCode {
+	case http.StatusOK:
+		return true, nil
+	case http.StatusUnauthorized:
+		return false, nil
+	default:
+		return false, fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
+	}
+}
+
 func (s Scanner) Type() detectorspb.DetectorType {
 	return detectorspb.DetectorType_Alegra
 }

pkg/detectors/alegra/alegra_integration_test.go

@@ -96,6 +96,7 @@ func TestAlegra_FromChunk(t *testing.T) {
 					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("Alegra.FromData() %s diff: (-got +want)\n%s", tt.name, diff)

pkg/detectors/alegra/alegra_test.go

@@ -14,7 +14,7 @@ import (
 var (
 	validPattern            = "wdvn-usa87a-fxp9ioas/[email protected]"
 	validSpecialCharPattern = "wdvn-usa87a-fxp9ioas / [email protected]"
-	invalidPattern          = "wdvn-usa87a-fxp9ioas/testUser$1005@example.com"
+	invalidPattern          = "wdvn-usa87a-fxp9ioasQQsstestUsQQ@example"
 )
 
 func TestAlegra_Pattern(t *testing.T) {
@@ -28,30 +28,30 @@ func TestAlegra_Pattern(t *testing.T) {
 	}{
 		{
 			name:  "valid pattern",
-			input: fmt.Sprintf("alegra: '%s'", validPattern),
-			want:  []string{"wdvn-usa87a-fxp9ioastestUser[email protected]"},
+			input: fmt.Sprintf("alegra: %s", validPattern),
+			want:  []string{"wdvn-usa87a-fxp9ioas:wdvn-usa87a-fxp9ioas/testUser[email protected]"},
 		},
 		{
 			name:  "valid pattern - with special characters",
-			input: fmt.Sprintf("alegra: '%s'", validSpecialCharPattern),
-			want:  []string{"wdvn-usa87a-fxp9ioastest[email protected]"},
+			input: fmt.Sprintf("alegra: %s", validSpecialCharPattern),
+			want:  []string{"wdvn-usa87a-fxp9ioas:test[email protected]"},
 		},
 		{
 			name:  "valid pattern - key out of prefix range",
-			input: fmt.Sprintf("alegra keyword is not close to the real key and id = '%s'", validPattern),
+			input: fmt.Sprintf("alegra keyword is not close to the real key and id = %s", validPattern),
 			want:  nil,
 		},
 		{
 			name:  "invalid pattern",
-			input: fmt.Sprintf("alegra: '%s'", invalidPattern),
+			input: fmt.Sprintf("alegra: %s", invalidPattern),
 			want:  nil,
 		},
 	}
 
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
 			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
-			if len(matchedDetectors) == 0 {
+			if len(matchedDetectors) == 0 && test.want != nil {
 				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
 				return
 			}
@@ -63,11 +63,7 @@ func TestAlegra_Pattern(t *testing.T) {
 			}
 
 			if len(results) != len(test.want) {
-				if len(results) == 0 {
-					t.Errorf("did not receive result")
-				} else {
-					t.Errorf("expected %d results, only received %d", len(test.want), len(results))
-				}
+				t.Errorf("expected %d results, got %d", len(test.want), len(results))
 				return
 			}
 

pkg/detectors/algoliaadminkey/algoliaadminkey.go

@@ -2,6 +2,8 @@ package algoliaadminkey
 
 import (
 	"context"
+	"fmt"
+	"encoding/json"
 	regexp "github.com/wasilibs/go-re2"
 	"net/http"
 	"strings"
@@ -22,14 +24,14 @@ 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{"algolia"}) + `\b([a-zA-Z0-9]{32})\b`)
-	idPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"algolia"}) + `\b([A-Z0-9]{10})\b`)
+	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"algolia", "docsearch", "apiKey"}) + `\b([a-zA-Z0-9]{32})\b`)
+	idPat  = regexp.MustCompile(detectors.PrefixRegex([]string{"algolia", "docsearch", "appId"}) + `\b([A-Z0-9]{10})\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{"algolia"}
+	return []string{"algolia", "docsearch"}
 }
 
 // FromData will find and optionally verify AlgoliaAdminKey secrets in a given set of bytes.
@@ -57,19 +59,16 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			}
 
 			if verify {
-				req, err := http.NewRequestWithContext(ctx, "GET", "https://"+resIdMatch+"-dsn.algolia.net/1/keys", nil)
-				if err != nil {
-					continue
-				}
-				req.Header.Add("X-Algolia-Application-Id", resIdMatch)
-				req.Header.Add("X-Algolia-API-Key", resMatch)
-				res, err := client.Do(req)
-				if err == nil {
-					defer res.Body.Close()
-					if res.StatusCode >= 200 && res.StatusCode < 300 {
-						s1.Verified = true
-					}
+				// Verify if the key is a valid Algolia Admin Key.
+				isVerified, verificationErr := verifyAlgoliaKey(ctx, resIdMatch, resMatch)
+
+				// Verify if the key has sensitive permissions, even if it's not an Admin Key.
+				if !isVerified {
+					isVerified, verificationErr = verifyAlgoliaKeyACL(ctx, resIdMatch, resMatch)
 				}
+
+				s1.SetVerificationError(verificationErr, resMatch)
+				s1.Verified = isVerified
 			}
 
 			results = append(results, s1)
@@ -78,6 +77,68 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 	return results, nil
 }
 
+func verifyAlgoliaKey(ctx context.Context, appId, apiKey string) (bool, error) {
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, "https://"+appId+"-dsn.algolia.net/1/keys", nil)
+	if err != nil {
+		return false, err
+	}
+
+	req.Header.Add("X-Algolia-Application-Id", appId)
+	req.Header.Add("X-Algolia-API-Key", apiKey)
+
+	res, err := client.Do(req)
+	if err != nil {
+		return false, err
+	}
+	defer res.Body.Close()
+
+	if res.StatusCode == 403 {
+		return false, nil
+	} else if res.StatusCode < 200 || res.StatusCode > 299 {
+		return false, fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
+	}
+
+	return true, nil
+}
+
+func verifyAlgoliaKeyACL(ctx context.Context, appId, apiKey string) (bool, error) {
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, "https://"+appId+".algolia.net/1/keys/"+apiKey, nil)
+	if err != nil {
+		return false, err
+	}
+
+	req.Header.Add("X-Algolia-Application-Id", appId)
+	req.Header.Add("X-Algolia-API-Key", apiKey)
+
+	res, err := client.Do(req)
+	if err != nil {
+		return false, err
+	}
+	defer res.Body.Close()
+
+	if res.StatusCode == 403 {
+		return false, nil
+	} else if res.StatusCode < 200 || res.StatusCode > 299 {
+		return false, fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
+	}
+
+	var jsonResponse struct {
+		ACL []string `json:"acl"`
+	}
+
+	if err := json.NewDecoder(res.Body).Decode(&jsonResponse); err != nil {
+		return false, err
+	}
+
+	for _, acl := range jsonResponse.ACL {
+		if acl != "search" && acl != "listIndexes" && acl != "settings" {
+			return true, nil // Other permissions are sensitive.
+		}
+	}
+
+	return false, nil
+}
+
 func (s Scanner) Type() detectorspb.DetectorType {
 	return detectorspb.DetectorType_AlgoliaAdminKey
 }

pkg/detectors/algoliaadminkey/algoliaadminkey_integration_test.go

@@ -51,6 +51,7 @@ func TestAlgoliaAdminKey_FromChunk(t *testing.T) {
 				{
 					DetectorType: detectorspb.DetectorType_AlgoliaAdminKey,
 					Verified:     true,
+					RawV2:        []byte(fmt.Sprintf("%s%s", secret, id)),
 				},
 			},
 			wantErr: false,
@@ -67,6 +68,7 @@ func TestAlgoliaAdminKey_FromChunk(t *testing.T) {
 				{
 					DetectorType: detectorspb.DetectorType_AlgoliaAdminKey,
 					Verified:     false,
+					RawV2:        []byte(fmt.Sprintf("%s%s", inactiveSecret, id)),
 				},
 			},
 			wantErr: false,