Add support for detecting and validating CastAI API tokens

pkg/detectors/aws/access_keys/accesskey.go

@@ -1,6 +1,7 @@
 package access_keys
 
 import (
+	"maps"
 	"context"
 	"fmt"
 	"net"
@@ -220,9 +221,7 @@ func (s scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 					}
 
 					// Append the extraData to the existing ExtraData map.
-					for k, v := range extraData {
-						s1.ExtraData[k] = v
-					}
+					maps.Copy(s1.ExtraData, extraData)
 					s1.SetVerificationError(verificationErr, secretMatch)
 				}
 			}

pkg/detectors/castai/castai.go

@@ -0,0 +1,145 @@
+package castai
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"maps"
+	"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/detector_typepb"
+)
+
+type scanner struct {
+	client *http.Client
+	detectors.EndpointSetter
+}
+
+func New(opts ...func(*scanner)) *scanner {
+	scanner := &scanner{}
+
+	// Default endpoints.
+	_ = scanner.SetConfiguredEndpoints(
+		"https://api.cast.ai/v1/kubernetes/external-clusters",
+		"https://api.eu.cast.ai/v1/kubernetes/external-clusters",
+	)
+
+	for _, opt := range opts {
+		opt(scanner)
+	}
+
+	return scanner
+}
+
+func WithClient(c *http.Client) func(*scanner) {
+	return func(s *scanner) {
+		s.client = c
+	}
+}
+
+// Ensure the Scanner satisfies the interface at compile time.
+var _ detectors.Detector = (*scanner)(nil)
+var _ detectors.EndpointCustomizer = (*scanner)(nil)
+var _ detectors.Versioner = (*scanner)(nil)
+
+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(castai_v1_[a-z0-9]{64}_[a-z0-9]{8})\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{"castai_v1_"} // Prefix
+}
+
+func (scanner) Version() int {
+	return 1
+}
+
+// FromData will find and optionally verify Castai 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)
+
+	uniqueMatches := make(map[string]struct{})
+	for _, match := range keyPat.FindAllStringSubmatch(dataStr, -1) {
+		uniqueMatches[match[1]] = struct{}{}
+	}
+
+	for match := range uniqueMatches {
+		s1 := detectors.Result{
+			DetectorType: detector_typepb.DetectorType_CastAI,
+			Raw:          []byte(match),
+			SecretParts:  map[string]string{"key": match},
+		}
+
+		if verify {
+			client := s.client
+			if client == nil {
+				client = defaultClient
+			}
+
+			for _, endpoint := range s.Endpoints() {
+				isVerified, extraData, verificationErr := verifyMatch(ctx, client, endpoint, match)
+				// A token can only be valid in a single environment.
+				if !isVerified && verificationErr == nil {
+					continue
+				}
+
+				s1.Verified = isVerified
+				s1.ExtraData = map[string]string{
+					"endpoint": endpoint,
+				}
+				maps.Copy(s1.ExtraData, extraData)
+				s1.SetVerificationError(verificationErr, match)
+				break
+			}
+		}
+
+		results = append(results, s1)
+	}
+
+	return
+}
+
+func verifyMatch(ctx context.Context, client *http.Client, endpoint string, token string) (bool, map[string]string, error) {
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
+	if err != nil {
+		return false, nil, err
+	}
+
+	req.Header.Set("X-API-Key", token)
+
+	res, err := client.Do(req)
+	if err != nil {
+		return false, nil, err
+	}
+	defer func() {
+		_, _ = io.Copy(io.Discard, res.Body)
+		_ = res.Body.Close()
+	}()
+
+	switch res.StatusCode {
+	case http.StatusOK:
+		// If the endpoint returns useful information, we can return it as a map.
+		return true, nil, nil
+	case http.StatusUnauthorized:
+		// The secret is determinately not verified (nothing to do)
+		return false, nil, nil
+	default:
+		return false, nil, fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
+	}
+}
+
+func (s scanner) Type() detector_typepb.DetectorType {
+	return detector_typepb.DetectorType_CastAI
+}
+
+func (s scanner) Description() string {
+	return "Castai is a blockchain development platform that provides a suite of tools and services for building and scaling decentralized applications. Castai API keys can be used to access these services."
+}

pkg/detectors/castai/castai_integration_test.go

@@ -0,0 +1,170 @@
+//go:build detectors
+// +build detectors
+
+package castai
+
+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/detector_typepb"
+)
+
+func TestCastai_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("CASTAI")
+	inactiveSecret := testSecrets.MustGetField("CASTAI_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:    New(),
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a castai secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detector_typepb.DetectorType_CastAI,
+					Verified:     true,
+					ExtraData: map[string]string{
+						"endpoint": "https://api.cast.ai/v1/kubernetes/external-clusters",
+					},
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    New(),
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a castai secret %s within but not valid", inactiveSecret)), // the secret would satisfy the regex but not pass validation
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detector_typepb.DetectorType_CastAI,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			name: "not found",
+			s:    New(),
+			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:    New(WithClient(common.SaneHttpClientTimeOut(1 * time.Microsecond))),
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a castai secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detector_typepb.DetectorType_CastAI,
+					Verified:     false,
+					ExtraData: map[string]string{
+						"endpoint": "https://api.cast.ai/v1/kubernetes/external-clusters",
+					},
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
+		},
+		{
+			name: "found, verified but unexpected api surface",
+			s:    New(WithClient(common.ConstantResponseHttpClient(404, ""))),
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte(fmt.Sprintf("You can find a castai secret %s within", secret)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detector_typepb.DetectorType_CastAI,
+					Verified:     false,
+					ExtraData: map[string]string{
+						"endpoint": "https://api.cast.ai/v1/kubernetes/external-clusters",
+					},
+				},
+			},
+			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("Castai.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", "RawV2", "verificationError", "primarySecret", "SecretParts")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Castai.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
+			}
+		})
+	}
+}
+
+func BenchmarkFromData(benchmark *testing.B) {
+	ctx := context.Background()
+	s := New()
+	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)
+				}
+			}
+		})
+	}
+}