Files
trufflehog/pkg/detectors/pinecone/pinecone_integration_test.go
ba0a524d6e Add Pinecone API key detector (#4917)
* Add Pinecone API key detector

Adds a new detector for Pinecone vector database API keys (pcsk_* format).

Detection:
- Regex matches the pcsk_{key_id}_{secret} structure with tight bounds
  (4+ char key ID, 40+ char secret, word boundaries) to minimize false positives.
- Extracts the embedded key_id from the token unconditionally, which maps to
  the key entry in the Pinecone console and aids revocation.

Verification:
- Uses GET /indexes (non-state-changing, read-only) with Api-Key header auth.
- Validates response body structure (requires "indexes" JSON key), not just
  status codes, to be resilient against API changes.
- 200: Verified. Extracts project_id from index host, total_indexes, and
  metadata for up to 5 indexes (name, host, cloud, region).
- 401: Invalid key (handles both plain text and JSON error bodies).
- 403: Valid key with restricted permissions (DataPlane-only roles).
  Marked as verified with permission=restricted metadata.

Uses common.SaneHttpClient() with standard timeouts (5s response, 2s dial,
3s TLS) and io.LimitReader (1MB cap) on response body. No SDK dependencies.

Registered as DetectorType Pinecone = 1048.

Made-with: Cursor

* Align Pinecone detector with SecretParts

Migrate Pinecone verification metadata to SecretParts, address the redundant 200-response JSON parsing Bugbot flagged, and add focused regression coverage for malformed verification responses.

* Refactor Pinecone detector and add tests

---------

Co-authored-by: Dylan Ayrey <[email protected]>
Co-authored-by: Dustin Decker <[email protected]>
Co-authored-by: Shahzad Haider <[email protected]>
Co-authored-by: Shahzad Haider <[email protected]>
2026-05-07 06:10:21 -04:00

162 lines
4.3 KiB
Go

//go:build detectors
// +build detectors
package pinecone
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 TestPinecone_FromChunk(t *testing.T) {
ctx, cancel := context.WithTimeout(context.Background(), time.Second*10)
defer cancel()
testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors6")
if err != nil {
t.Fatalf("could not get test secrets from GCP: %s", err)
}
secret := testSecrets.MustGetField("PINECONE")
inactiveSecret := testSecrets.MustGetField("PINECONE_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 pinecone secret %s within", secret)),
verify: true,
},
want: []detectors.Result{
{
DetectorType: detector_typepb.DetectorType_Pinecone,
Verified: true,
},
},
wantErr: false,
wantVerificationErr: false,
},
{
name: "found, unverified",
s: Scanner{},
args: args{
ctx: context.Background(),
data: []byte(fmt.Sprintf("You can find a pinecone secret %s within but not valid", inactiveSecret)),
verify: true,
},
want: []detectors.Result{
{
DetectorType: detector_typepb.DetectorType_Pinecone,
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 pinecone secret %s within", secret)),
verify: true,
},
want: []detectors.Result{
{
DetectorType: detector_typepb.DetectorType_Pinecone,
Verified: false,
},
},
wantErr: false,
wantVerificationErr: true,
},
{
name: "found, unexpected api surface",
s: Scanner{client: common.ConstantResponseHttpClient(500, "")},
args: args{
ctx: context.Background(),
data: []byte(fmt.Sprintf("You can find a pinecone secret %s within", secret)),
verify: true,
},
want: []detectors.Result{
{
DetectorType: detector_typepb.DetectorType_Pinecone,
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("Pinecone.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", "Redacted", "ExtraData", "SecretParts", "verificationError", "primarySecret")
if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
t.Errorf("Pinecone.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)
}
}
})
}
}