feat(typeform): add v2 detector for new key formats (#3660)

docs:
- https://www.typeform.com/developers/get-started/personal-access-token/

40 to 59 chars is set because we've seen tokens with an extra 15 bytes at the end, the base key is 40 bytes long

pkg/detectors/typeform/typeform.go → pkg/detectors/typeform/v1/typeform.go

@@ -3,10 +3,11 @@ package typeform
 import (
 	"context"
 	"fmt"
-	regexp "github.com/wasilibs/go-re2"
 	"net/http"
 	"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"
@@ -24,6 +25,8 @@ var (
 	keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"typeform"}) + `\b([0-9A-Za-z]{44})\b`)
 )
 
+func (s Scanner) Version() int { return 1 }
+
 // Keywords are used for efficiently pre-filtering chunks.
 // Use identifiers in the secret preferably, or the provider name.
 func (s Scanner) Keywords() []string {

pkg/detectors/typeform/v2/typeform.go

@@ -0,0 +1,104 @@
+package typeform
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+
+	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{}
+
+// Ensure the Scanner satisfies the interface at compile time.
+var _ detectors.Detector = (*Scanner)(nil)
+
+var (
+	client = common.SaneHttpClient()
+
+	keyPat = regexp.MustCompile(`\btfp_[a-zA-Z0-9_]{40,59}\b`)
+)
+
+func (s Scanner) Version() int { return 2 }
+
+// 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{"tfp_"}
+}
+
+type TypeFormResponse struct {
+	UserID   string `json:"user_id,omitempty"`
+	Email    string `json:"email,omitempty"`
+	Alias    string `json:"alias,omitempty"`
+	Language string `json:"language,omitempty"`
+}
+
+// FromData will find and optionally verify Typeform 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.FindAllString(dataStr, -1)
+
+	for _, match := range matches {
+		s1 := detectors.Result{
+			DetectorType: detectorspb.DetectorType_Typeform,
+			Raw:          []byte(match),
+		}
+
+		if verify {
+			verified, typeformResponse, requestErr := verifyMatch(ctx, client, match)
+			s1.Verified = verified
+			if requestErr != nil {
+				s1.SetVerificationError(err, match)
+			} else {
+				s1.ExtraData = map[string]string{
+					"UserId":   typeformResponse.UserID,
+					"Email":    typeformResponse.Email,
+					"Alias":    typeformResponse.Alias,
+					"Language": typeformResponse.Language,
+				}
+			}
+		}
+		results = append(results, s1)
+
+	}
+
+	return results, nil
+}
+
+func verifyMatch(ctx context.Context, client *http.Client, secret string) (bool, TypeFormResponse, error) {
+	var response TypeFormResponse
+
+	req, err := http.NewRequestWithContext(ctx, "GET", "https://api.typeform.com/me", nil)
+	if err != nil {
+		return false, response, nil
+	}
+	req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", secret))
+	res, err := client.Do(req)
+	if err != nil {
+		return false, response, err
+	}
+	defer res.Body.Close()
+	if err = json.NewDecoder(res.Body).Decode(&response); err != nil {
+		return false, response, err
+	}
+	if res.StatusCode == 200 {
+		return true, response, nil
+	} else {
+		return false, response, fmt.Errorf("unexpected status code %d", res.StatusCode)
+	}
+}
+
+func (s Scanner) Type() detectorspb.DetectorType {
+	return detectorspb.DetectorType_Typeform
+}
+
+func (s Scanner) Description() string {
+	return "Typeform is a service for creating forms and surveys. Typeform API keys can be used to access and manage forms and responses."
+}

pkg/detectors/typeform/v2/typeform_integration_test.go

@@ -0,0 +1,161 @@
+//go:build detectors
+// +build detectors
+
+package typeform
+
+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/pb/detectorspb"
+)
+
+func TestTypeform_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("TYPEFORM_V2")
+	inactiveSecret := testSecrets.MustGetField("TYPEFORM_V2_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 typeform secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Typeform,
+					Verified:     true,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a typeform 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_Typeform,
+					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,
+		},
+		{
+			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 a typeform secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Typeform,
+					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 a typeform secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Typeform,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+	}
+	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("TypeForm.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("TypeForm.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/detectors/typeform/v2/typeform_test.go

@@ -0,0 +1,79 @@
+package typeform
+
+import (
+	"context"
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/engine/ahocorasick"
+)
+
+func TestTypeformV2_Pattern(t *testing.T) {
+	d := Scanner{}
+	ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d})
+	tests := []struct {
+		name  string
+		input string
+		want  []string
+	}{
+		{
+			name:  "typical pattern (v2)",
+			input: "typeform_token = 'tfp_ABCDEfghijKLMNOPqrstuvWXYZ0123456789ABCDEFGH_ijK12340qqqBBB'",
+			want:  []string{"tfp_ABCDEfghijKLMNOPqrstuvWXYZ0123456789ABCDEFGH_ijK12340qqqBBB"},
+		},
+		{
+			name: "finds all matches (v2)",
+			input: `typeform_token1 = 'tfp_ABCDEfghijKLMNOPqrstuvWXYZ0123456789ABCDEFGH_ijK12340qqqBBB'
+typeform_token2 = 'tfp_943af478d3ff3d4d760020c11af102b79c440513'`,
+			want: []string{"tfp_ABCDEfghijKLMNOPqrstuvWXYZ0123456789ABCDEFGH_ijK12340qqqBBB", "tfp_943af478d3ff3d4d760020c11af102b79c440513"},
+		},
+		{
+			name:  "invalid pattern",
+			input: "typeform_token = 'tfp_1'",
+			want:  []string{},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			matchedDetectors := ahoCorasickCore.FindDetectorMatches([]byte(test.input))
+			if len(matchedDetectors) == 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)
+			}
+		})
+	}
+}

pkg/engine/defaults/defaults.go

@@ -743,7 +743,8 @@ import (
 	twitterv2 "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/twitter/v2"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/twitterconsumerkey"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/tyntec"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/typeform"
+	typeformv1 "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/typeform/v1"
+	typeformv2 "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/typeform/v2"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/typetalk"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/ubidots"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/uclassify"
@@ -1586,7 +1587,8 @@ func buildDetectorList() []detectors.Detector {
 		&twitterv1.Scanner{},
 		&twitterv2.Scanner{},
 		&tyntec.Scanner{},
-		&typeform.Scanner{},
+		&typeformv1.Scanner{},
+		&typeformv2.Scanner{},
 		&typetalk.Scanner{},
 		&ubidots.Scanner{},
 		&uclassify.Scanner{},