Detector-Competition-Feat: Added Replicate API token detector (#2021)

* Detector-Competition-Feat: Added Replicate API token detector

* fix fullstory

---------

Co-authored-by: Zachary Rice <zachary.rice@trufflesec.com>

pkg/detectors/fullstory_v2/fullstory_v2.go

@@ -18,7 +18,7 @@ type Scanner struct{}
 var _ detectors.Detector = (*Scanner)(nil)
 var _ detectors.Versioner = (*Scanner)(nil)
 
-func (Scanner) Version() int            { return 1 }
+func (Scanner) Version() int { return 2 }
 
 var (
 	client = common.SaneHttpClient()

pkg/detectors/replicate/replicate.go

@@ -0,0 +1,85 @@
+package replicate
+
+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 {
+	client *http.Client
+}
+
+// Ensure the Scanner satisfies the interface at compile time.
+var _ detectors.Detector = (*Scanner)(nil)
+
+var (
+	defaultClient = common.SaneHttpClient()
+	keyPat = regexp.MustCompile(`\b(r8_[0-9A-Za-z-_]{37})\b`)
+)
+
+func (s Scanner) Keywords() []string {
+	return []string{"replicate", "r8_"}
+}
+
+func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
+	dataStr := string(data)
+
+	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+
+	for _, match := range matches {
+		if len(match) != 2 {
+			continue
+		}
+		resMatch := strings.TrimSpace(match[1])
+
+		s1 := detectors.Result{
+			DetectorType: detectorspb.DetectorType_Replicate,
+			Raw:          []byte(resMatch),
+		}
+
+		if verify {
+			client := s.client
+			if client == nil {
+				client = defaultClient
+			}
+			req, err := http.NewRequestWithContext(ctx, "GET", "https://api.replicate.com/v1/predictions", nil)
+			if err != nil {
+				continue
+			}
+			req.Header.Add("Authorization", fmt.Sprintf("Token %s", 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 res.StatusCode == 401 {
+					// The secret is determinately not verified (nothing to do)
+				} else {
+					s1.VerificationError = fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
+				}
+			} else {
+				s1.VerificationError = err
+			}
+		}
+
+		// 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 !s1.Verified && detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
+			continue
+		}
+
+		results = append(results, s1)
+	}
+
+	return results, nil
+}
+
+func (s Scanner) Type() detectorspb.DetectorType {
+	return detectorspb.DetectorType_Replicate
+}

pkg/detectors/replicate/replicate_test.go

@@ -0,0 +1,128 @@
+//go:build detectors
+// +build detectors
+
+package replicate
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestReplicate_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)
+	}
+	secret := testSecrets.MustGetField("REPLICATE")
+	inactiveSecret := testSecrets.MustGetField("REPLICATE_INACTIVE")
+
+	type args struct {
+		ctx    context.Context
+		data   []byte
+		verify bool
+	}
+	tests := []struct {
+		name                string
+		s                   Scanner
+		args                args
+		want                []detectors.Result
+		wantErr             bool
+		wantVerificationErr bool
+	}{
+		{
+			name: "found, verified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a replicate secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Replicate,
+					Verified:     true,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a replicate secret %s within but not valid", inactiveSecret)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Replicate,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: 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,
+			wantVerificationErr: false,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Replicate.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])
+				}
+				if (got[i].VerificationError != nil) != tt.wantVerificationErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.wantVerificationErr, got[i].VerificationError)
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "VerificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Replicate.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
+			}
+		})
+	}
+}
+
+func BenchmarkFromData(benchmark *testing.B) {
+	ctx := context.Background()
+	s := Scanner{}
+	for name, data := range detectors.MustGetBenchmarkData() {
+		benchmark.Run(name, func(b *testing.B) {
+			b.ResetTimer()
+			for n := 0; n < b.N; n++ {
+				_, err := s.FromData(ctx, false, data)
+				if err != nil {
+					b.Fatal(err)
+				}
+			}
+		})
+	}
+}

pkg/engine/defaults.go

@@ -549,6 +549,7 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/refiner"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/rentman"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/repairshopr"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/replicate"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/replyio"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/requestfinance"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/restpack"
@@ -1584,6 +1585,7 @@ func DefaultDetectors() []detectors.Detector {
 		eventbrite.Scanner{},
 		&overloop.Scanner{},
 		ngrok.Scanner{},
+		replicate.Scanner{},
 	}
 
 }

pkg/pb/detectorspb/detectors.pb.go

@@ -1049,6 +1049,7 @@ const (
 	DetectorType_RequestFinance            DetectorType = 964
 	DetectorType_Overloop                  DetectorType = 965
 	DetectorType_Ngrok                     DetectorType = 966
+	DetectorType_Replicate                 DetectorType = 967
 )
 
 // Enum value maps for DetectorType.
@@ -2017,6 +2018,7 @@ var (
 		964: "RequestFinance",
 		965: "Overloop",
 		966: "Ngrok",
+		967: "Replicate",
 	}
 	DetectorType_value = map[string]int32{
 		"Alibaba":                       0,
@@ -2982,6 +2984,7 @@ var (
 		"RequestFinance":                964,
 		"Overloop":                      965,
 		"Ngrok":                         966,
+		"Replicate":                     967,
 	}
 )
 
@@ -3360,7 +3363,7 @@ 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, 0xd7, 0x79, 0x0a, 0x0c, 0x44,
+	0x09, 0x0a, 0x05, 0x55, 0x54, 0x46, 0x31, 0x36, 0x10, 0x03, 0x2a, 0xe7, 0x79, 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,
@@ -4334,7 +4337,8 @@ var file_detectors_proto_rawDesc = []byte{
 	0x74, 0x10, 0xc3, 0x07, 0x12, 0x13, 0x0a, 0x0e, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x46,
 	0x69, 0x6e, 0x61, 0x6e, 0x63, 0x65, 0x10, 0xc4, 0x07, 0x12, 0x0d, 0x0a, 0x08, 0x4f, 0x76, 0x65,
 	0x72, 0x6c, 0x6f, 0x6f, 0x70, 0x10, 0xc5, 0x07, 0x12, 0x0a, 0x0a, 0x05, 0x4e, 0x67, 0x72, 0x6f,
-	0x6b, 0x10, 0xc6, 0x07, 0x42, 0x3d, 0x5a, 0x3b, 0x67, 0x69, 0x74, 0x68, 0x75, 0x62, 0x2e, 0x63,
+	0x6b, 0x10, 0xc6, 0x07, 0x12, 0x0e, 0x0a, 0x09, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74,
+	0x65, 0x10, 0xc7, 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,

proto/detectors.proto

@@ -975,6 +975,7 @@ enum DetectorType {
   RequestFinance = 964;
   Overloop = 965;
   Ngrok = 966;
+  Replicate = 967;
 }
 
 message Result {