add thog enterprise detector for web keys (#1448)

* saving progress

* proto changes

* run make protos

* verify response, add test case

* resolve linter warning about unescaped . in regex pattern

* resolve overlapping proto number

pkg/detectors/trufflehogenterprise/trufflehogenterprise.go

@@ -0,0 +1,108 @@
+package trufflehogenterprise
+
+import (
+	"context"
+	"fmt"
+	"net/http"
+	"regexp"
+	"strings"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+type Scanner struct{}
+
+// Ensure the Scanner satisfies the interface at compile time.
+var _ detectors.Detector = (*Scanner)(nil)
+
+var (
+	client = common.SaneHttpClient()
+
+	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
+	keyPat      = regexp.MustCompile(`\bthog-key-[0-9a-f]{16}\b`)
+	secretPat   = regexp.MustCompile(`\bthog-secret-[0-9a-f]{32}\b`)
+	hostnamePat = regexp.MustCompile(`\b[a-z]+-[a-z]+-[a-z]+\.[a-z][0-9]\.[a-z]+\.trufflehog\.org\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{"thog"}
+}
+
+// FromData will find and optionally verify Trufflehog Enterprise 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)
+
+	keyMatches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	secretMatches := secretPat.FindAllStringSubmatch(dataStr, -1)
+	hostnameMatches := hostnamePat.FindAllStringSubmatch(dataStr, -1)
+
+	for _, keyMatch := range keyMatches {
+		if len(keyMatch) != 1 {
+			continue
+		}
+		resKeyMatch := strings.TrimSpace(keyMatch[0])
+		for _, secretMatch := range secretMatches {
+
+			if len(secretMatch) != 1 {
+				continue
+			}
+			resSecretMatch := strings.TrimSpace(secretMatch[0])
+
+			for _, hostnameMatch := range hostnameMatches {
+				if len(hostnameMatch) != 1 {
+					continue
+				}
+
+				resHostnameMatch := strings.TrimSpace(hostnameMatch[0])
+
+				s1 := detectors.Result{
+					DetectorType: detectorspb.DetectorType_TrufflehogEnterprise,
+					Raw:          []byte(resKeyMatch),
+				}
+
+				if verify {
+					endpoint := fmt.Sprintf("https://%s/api/v1/sources", resHostnameMatch)
+					req, err := http.NewRequestWithContext(ctx, "GET", endpoint, nil)
+					if err != nil {
+						continue
+					}
+
+					req.Header.Add("Accept", "application/vnd.trufflehogenterprise+json; version=3")
+					req.Header.Add("X-Thog-Secret", resSecretMatch)
+					req.Header.Add("X-Thog-Key", resKeyMatch)
+
+					res, err := client.Do(req)
+					if err == nil {
+						verifiedBodyResponse, err := common.ResponseContainsSubstring(res.Body, "data")
+						if err != nil {
+							return nil, err
+						}
+
+						defer res.Body.Close()
+
+						if res.StatusCode >= 200 && res.StatusCode < 300 && verifiedBodyResponse {
+							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(resSecretMatch, detectors.DefaultFalsePositives, true) {
+								continue
+							}
+						}
+					}
+				}
+
+				results = append(results, s1)
+			}
+		}
+	}
+
+	return results, nil
+}
+
+func (s Scanner) Type() detectorspb.DetectorType {
+	return detectorspb.DetectorType_TrufflehogEnterprise
+}

pkg/detectors/trufflehogenterprise/trufflehogenterprise_test.go

@@ -0,0 +1,121 @@
+//go:build detectors
+// +build detectors
+
+package trufflehogenterprise
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/kylelemons/godebug/pretty"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestTrufflehogenterprise_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors5")
+	if err != nil {
+		t.Fatalf("could not get test secrets from GCP: %s", err)
+	}
+	host := testSecrets.MustGetField("THOG_HOSTNAME")
+	key := testSecrets.MustGetField("THOG_WEB_KEY")
+	secret := testSecrets.MustGetField("THOG_WEB_SECRET")
+	inactiveSecret := testSecrets.MustGetField("THOG_WEB_INACTIVE_SECRET")
+
+	type args struct {
+		ctx    context.Context
+		data   []byte
+		verify bool
+	}
+	tests := []struct {
+		name    string
+		s       Scanner
+		args    args
+		want    []detectors.Result
+		wantErr bool
+	}{
+		{
+			name: "found, verified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a thog secret %s for %s with key %s within", secret, host, key)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_TrufflehogEnterprise,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a trufflehogenterprise secret %s for %s with key %s within but not valid", inactiveSecret, host, key)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_TrufflehogEnterprise,
+					Verified:     false,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "not found",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte("You cannot find the secret within"),
+				verify: true,
+			},
+			want:    nil,
+			wantErr: false,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			s := Scanner{}
+			got, err := s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Trufflehogenterprise.FromData() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			for i := range got {
+				if len(got[i].Raw) == 0 {
+					t.Fatalf("no raw secret present: \n %+v", got[i])
+				}
+				got[i].Raw = nil
+			}
+			if diff := pretty.Compare(got, tt.want); diff != "" {
+				t.Errorf("Trufflehogenterprise.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
+			}
+		})
+	}
+}
+
+func BenchmarkFromData(benchmark *testing.B) {
+	ctx := context.Background()
+	s := Scanner{}
+	for name, data := range detectors.MustGetBenchmarkData() {
+		benchmark.Run(name, func(b *testing.B) {
+			for n := 0; n < b.N; n++ {
+				_, err := s.FromData(ctx, false, data)
+				if err != nil {
+					b.Fatal(err)
+				}
+			}
+		})
+	}
+}

pkg/pb/detectorspb/detectors.pb.go

@@ -993,6 +993,7 @@ const (
 	DetectorType_Docusign                      DetectorType = 919
 	DetectorType_Couchbase                     DetectorType = 920
 	DetectorType_EnvoyApiKey                   DetectorType = 921
+	DetectorType_TrufflehogEnterprise          DetectorType = 922
 )
 
 // Enum value maps for DetectorType.
@@ -1916,6 +1917,7 @@ var (
 		919: "Docusign",
 		920: "Couchbase",
 		921: "EnvoyApiKey",
+		922: "TrufflehogEnterprise",
 	}
 	DetectorType_value = map[string]int32{
 		"Alibaba":                       0,
@@ -2836,6 +2838,7 @@ var (
 		"Docusign":                      919,
 		"Couchbase":                     920,
 		"EnvoyApiKey":                   921,
+		"TrufflehogEnterprise":          922,
 	}
 )
 
@@ -3214,7 +3217,7 @@ var file_detectors_proto_rawDesc = []byte{
 	0x44, 0x65, 0x63, 0x6f, 0x64, 0x65, 0x72, 0x54, 0x79, 0x70, 0x65, 0x12, 0x0b, 0x0a, 0x07, 0x55,
 	0x4e, 0x4b, 0x4e, 0x4f, 0x57, 0x4e, 0x10, 0x00, 0x12, 0x09, 0x0a, 0x05, 0x50, 0x4c, 0x41, 0x49,
 	0x4e, 0x10, 0x01, 0x12, 0x0a, 0x0a, 0x06, 0x42, 0x41, 0x53, 0x45, 0x36, 0x34, 0x10, 0x02, 0x12,
-	0x09, 0x0a, 0x05, 0x55, 0x54, 0x46, 0x31, 0x36, 0x10, 0x03, 0x2a, 0x9b, 0x73, 0x0a, 0x0c, 0x44,
+	0x09, 0x0a, 0x05, 0x55, 0x54, 0x46, 0x31, 0x36, 0x10, 0x03, 0x2a, 0xb6, 0x73, 0x0a, 0x0c, 0x44,
 	0x65, 0x74, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x54, 0x79, 0x70, 0x65, 0x12, 0x0b, 0x0a, 0x07, 0x41,
 	0x6c, 0x69, 0x62, 0x61, 0x62, 0x61, 0x10, 0x00, 0x12, 0x08, 0x0a, 0x04, 0x41, 0x4d, 0x51, 0x50,
 	0x10, 0x01, 0x12, 0x07, 0x0a, 0x03, 0x41, 0x57, 0x53, 0x10, 0x02, 0x12, 0x09, 0x0a, 0x05, 0x41,
@@ -4136,11 +4139,13 @@ var file_detectors_proto_rawDesc = []byte{
 	0x66, 0x65, 0x63, 0x74, 0x10, 0x96, 0x07, 0x12, 0x0d, 0x0a, 0x08, 0x44, 0x6f, 0x63, 0x75, 0x73,
 	0x69, 0x67, 0x6e, 0x10, 0x97, 0x07, 0x12, 0x0e, 0x0a, 0x09, 0x43, 0x6f, 0x75, 0x63, 0x68, 0x62,
 	0x61, 0x73, 0x65, 0x10, 0x98, 0x07, 0x12, 0x10, 0x0a, 0x0b, 0x45, 0x6e, 0x76, 0x6f, 0x79, 0x41,
-	0x70, 0x69, 0x4b, 0x65, 0x79, 0x10, 0x99, 0x07, 0x42, 0x3d, 0x5a, 0x3b, 0x67, 0x69, 0x74, 0x68,
-	0x75, 0x62, 0x2e, 0x63, 0x6f, 0x6d, 0x2f, 0x74, 0x72, 0x75, 0x66, 0x66, 0x6c, 0x65, 0x73, 0x65,
-	0x63, 0x75, 0x72, 0x69, 0x74, 0x79, 0x2f, 0x74, 0x72, 0x75, 0x66, 0x66, 0x6c, 0x65, 0x68, 0x6f,
-	0x67, 0x2f, 0x76, 0x33, 0x2f, 0x70, 0x6b, 0x67, 0x2f, 0x70, 0x62, 0x2f, 0x64, 0x65, 0x74, 0x65,
-	0x63, 0x74, 0x6f, 0x72, 0x73, 0x70, 0x62, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33,
+	0x70, 0x69, 0x4b, 0x65, 0x79, 0x10, 0x99, 0x07, 0x12, 0x19, 0x0a, 0x14, 0x54, 0x72, 0x75, 0x66,
+	0x66, 0x6c, 0x65, 0x68, 0x6f, 0x67, 0x45, 0x6e, 0x74, 0x65, 0x72, 0x70, 0x72, 0x69, 0x73, 0x65,
+	0x10, 0x9a, 0x07, 0x42, 0x3d, 0x5a, 0x3b, 0x67, 0x69, 0x74, 0x68, 0x75, 0x62, 0x2e, 0x63, 0x6f,
+	0x6d, 0x2f, 0x74, 0x72, 0x75, 0x66, 0x66, 0x6c, 0x65, 0x73, 0x65, 0x63, 0x75, 0x72, 0x69, 0x74,
+	0x79, 0x2f, 0x74, 0x72, 0x75, 0x66, 0x66, 0x6c, 0x65, 0x68, 0x6f, 0x67, 0x2f, 0x76, 0x33, 0x2f,
+	0x70, 0x6b, 0x67, 0x2f, 0x70, 0x62, 0x2f, 0x64, 0x65, 0x74, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x73,
+	0x70, 0x62, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33,
 }
 
 var (

proto/detectors.proto

@@ -930,6 +930,7 @@ enum DetectorType {
   Docusign = 919;
   Couchbase = 920;
   EnvoyApiKey = 921;
+  TrufflehogEnterprise = 922;
 }
 
 message Result {