Add "Intra42" detector (#2835)

* Add basic intra42 detector (lacks verification)

* Improve keywords/prefixes for intra42 detector

* Un-lint pkg/pb/detectorspb/detectors.pb.go to avoid bloating PR

* Add client_id match and secret verification

* Improve PrefixRegex

* Add missing entry in DetectorType_name in detectors.pb.go

* Add Intra42 to proto/detectors.proto

* Remove PrefixRegex

* Keep only identifiers as keywords

* Factorize regex (a-f0-9)

pkg/detectors/intra42/intra42.go

@@ -0,0 +1,117 @@
+package intra42
+
+import (
+	"context"
+	"fmt"
+	"net/http"
+	"net/url"
+	"strconv"
+	"strings"
+
+	regexp "github.com/wasilibs/go-re2"
+
+	"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)
+
+const verifyURL = "https://api.intra.42.fr/oauth/token"
+
+var (
+	defaultClient = common.SaneHttpClient()
+
+	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives
+	keyPat = regexp.MustCompile(`\b(s-s4t2(?:ud|af)-[a-f0-9]{64})\b`)
+	idPat  = regexp.MustCompile(`\b(u-s4t2(?:ud|af)-[a-f0-9]{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{"s-s4t2ud-", "s-s4t2af-"}
+}
+
+// FromData will find and optionally verify Intra42 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)
+
+	for _, match := range matches {
+		if len(match) != 2 {
+			continue
+		}
+		resMatch := strings.TrimSpace(match[1])
+
+		for _, idMatch := range idMatches {
+			if len(idMatch) != 2 {
+				continue
+			}
+			resIdMatch := strings.TrimSpace(idMatch[1])
+
+			s1 := detectors.Result{
+				DetectorType: detectorspb.DetectorType_Intra42,
+				Raw:          []byte(resMatch),
+			}
+
+			if verify {
+				client := s.getClient()
+				isVerified, verificationErr := verifyIntra42(ctx, client, resMatch, resIdMatch)
+				s1.Verified = isVerified
+				s1.SetVerificationError(verificationErr, resMatch)
+			}
+
+			results = append(results, s1)
+		}
+	}
+	return results, nil
+}
+
+func (s Scanner) getClient() *http.Client {
+	if s.client != nil {
+		return s.client
+	}
+	return defaultClient
+}
+
+func verifyIntra42(ctx context.Context, client *http.Client, resMatch string, resIdMatch string) (bool, error) {
+	data := url.Values{}
+	data.Set("client_id", resIdMatch)
+	data.Set("client_secret", resMatch)
+	data.Set("grant_type", "client_credentials")
+	encodedData := data.Encode()
+
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, verifyURL, strings.NewReader(encodedData))
+	if err != nil {
+		return false, err
+	}
+
+	req.Header.Add("Content-Type", "application/x-www-form-urlencoded")
+	req.Header.Add("Content-Length", strconv.Itoa(len(data.Encode())))
+	res, err := client.Do(req)
+	if err != nil {
+		return false, err
+	}
+	defer 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_Intra42
+}

pkg/detectors/intra42/intra42_test.go

@@ -0,0 +1,223 @@
+//go:build detectors
+// +build detectors
+
+package intra42
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestIntra42_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
+	tests := []struct {
+		name  string
+		input string
+		want  []string
+	}{
+		{
+			name: "typical pattern",
+			input: `
+intra_client_id = 'u-s4t2ud-d91c558a2ba6b47f60f690efc20a33d28c252d5bed8400343246f3eb68f490d2'
+intra_client_secret = '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'
+`,
+			want: []string{
+				"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",
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			chunkSpecificDetectors := make(map[ahocorasick.DetectorKey]detectors.Detector, 2)
+			ahoCorasickCore.PopulateMatchingDetectors(test.input, chunkSpecificDetectors)
+			if len(chunkSpecificDetectors) == 0 {
+				t.Errorf("keywords '%v' not matched by: %s", d.Keywords(), test.input)
+				return
+			}
+
+			results, err := d.FromData(context.Background(), false, []byte(test.input))
+			if err != nil {
+				t.Errorf("error = %v", err)
+				return
+			}
+
+			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))
+				}
+				return
+			}
+
+			actual := make(map[string]struct{}, len(results))
+			for _, r := range results {
+				if len(r.RawV2) > 0 {
+					actual[string(r.RawV2)] = struct{}{}
+				} else {
+					actual[string(r.Raw)] = struct{}{}
+				}
+			}
+			expected := make(map[string]struct{}, len(test.want))
+			for _, v := range test.want {
+				expected[v] = struct{}{}
+			}
+
+			if diff := cmp.Diff(expected, actual); diff != "" {
+				t.Errorf("%s diff: (-want +got)\n%s", test.name, diff)
+			}
+		})
+	}
+}
+
+func TestIntra42_FromChunk(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*10)
+	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("INTRA42_SECRET")
+	id := testSecrets.MustGetField("INTRA42_ID")
+	inactiveSecret := testSecrets.MustGetField("INTRA42_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 an intra42 secret %s within intra42 %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Intra42,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, would be verified if not for timeout",
+			s:    Scanner{client: common.SaneHttpClientTimeOut(1 * time.Microsecond)},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find an intra42 secret %s within intra42 %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Intra42,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, verified but unexpected api surface",
+			s:    Scanner{client: common.ConstantResponseHttpClient(404, "")},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find an intra42 secret %s within intra42 %s", secret, id)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Intra42,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find an intra42 secret %s within intra42 %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Intra42,
+					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) {
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Intra42.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.Errorf("Intra42.FromData() verificationError = %v, wantVerificationErr %v", got[i].VerificationError(), tt.wantVerificationErr)
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Intra42.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

@@ -347,6 +347,7 @@ import (
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/integromat"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/intercom"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/interseller"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/intra42"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/intrinio"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/invoiceocean"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/ip2location"
@@ -1604,6 +1605,7 @@ func DefaultDetectors() []detectors.Detector {
 		gcpapplicationdefaultcredentials.Scanner{},
 		wiz.Scanner{},
 		onfleet.Scanner{},
+		intra42.Scanner{},
 	}
 }
 

pkg/pb/detectorspb/detectors.pb.go

@@ -1085,6 +1085,7 @@ const (
 	DetectorType_Wiz                                     DetectorType = 984
 	DetectorType_Pagarme                                 DetectorType = 985
 	DetectorType_Onfleet                                 DetectorType = 986
+	DetectorType_Intra42                                 DetectorType = 987
 )
 
 // Enum value maps for DetectorType.
@@ -2073,6 +2074,7 @@ var (
 		984: "Wiz",
 		985: "Pagarme",
 		986: "Onfleet",
+		987: "Intra42",
 	}
 	DetectorType_value = map[string]int32{
 		"Alibaba":                               0,
@@ -3058,6 +3060,7 @@ var (
 		"Wiz":                              984,
 		"Pagarme":                          985,
 		"Onfleet":                          986,
+		"Intra42":                          987,
 	}
 )
 

proto/detectors.proto

@@ -996,6 +996,7 @@ enum DetectorType {
   Wiz = 984;
   Pagarme = 985;
   Onfleet = 986;
+  Intra42 = 987;
 }
 
 message Result {