-
Notifications
You must be signed in to change notification settings - Fork 1.7k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* adding Groq detector * using prefix as keyword
- Loading branch information
Showing
5 changed files
with
331 additions
and
7 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,97 @@ | ||
package groq | ||
|
||
import ( | ||
"context" | ||
"fmt" | ||
"io" | ||
"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 { | ||
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(gsk_[a-zA-Z0-9]{52})\b`) | ||
) | ||
|
||
func (s Scanner) Keywords() []string { | ||
return []string{"gsk_"} | ||
} | ||
|
||
// FromData will find and optionally verify Groq 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: detectorspb.DetectorType_Groq, | ||
Raw: []byte(match), | ||
} | ||
|
||
if verify { | ||
client := s.client | ||
if client == nil { | ||
client = defaultClient | ||
} | ||
|
||
isVerified, extraData, verificationErr := verifyMatch(ctx, client, match) | ||
s1.Verified = isVerified | ||
s1.ExtraData = extraData | ||
s1.SetVerificationError(verificationErr, match) | ||
} | ||
|
||
results = append(results, s1) | ||
} | ||
|
||
return | ||
} | ||
|
||
func verifyMatch(ctx context.Context, client *http.Client, token string) (bool, map[string]string, error) { | ||
// https://console.groq.com/docs/models | ||
// This endpoint will return a JSON list of all active models. | ||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, "https://api.groq.com/openai/v1/models", nil) | ||
if err != nil { | ||
return false, nil, nil | ||
} | ||
req.Header.Add("Authorization", "Bearer "+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() detectorspb.DetectorType { | ||
return detectorspb.DetectorType_Groq | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,221 @@ | ||
//go:build detectors | ||
// +build detectors | ||
|
||
package groq | ||
|
||
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 TestGroq_Pattern(t *testing.T) { | ||
d := Scanner{} | ||
ahoCorasickCore := ahocorasick.NewAhoCorasickCore([]detectors.Detector{d}) | ||
tests := []struct { | ||
name string | ||
input string | ||
want []string | ||
}{ | ||
{ | ||
name: "typical pattern", | ||
input: "groq_token = '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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 TestGroq_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("GROQ") | ||
inactiveSecret := testSecrets.MustGetField("GROQ_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 groq secret %s within", secret)), | ||
verify: true, | ||
}, | ||
want: []detectors.Result{ | ||
{ | ||
DetectorType: detectorspb.DetectorType_Groq, | ||
Verified: true, | ||
}, | ||
}, | ||
wantErr: false, | ||
wantVerificationErr: false, | ||
}, | ||
{ | ||
name: "found, unverified", | ||
s: Scanner{}, | ||
args: args{ | ||
ctx: context.Background(), | ||
data: []byte(fmt.Sprintf("You can find a groq 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_Groq, | ||
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 groq secret %s within", secret)), | ||
verify: true, | ||
}, | ||
want: []detectors.Result{ | ||
{ | ||
DetectorType: detectorspb.DetectorType_Groq, | ||
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 groq secret %s within", secret)), | ||
verify: true, | ||
}, | ||
want: []detectors.Result{ | ||
{ | ||
DetectorType: detectorspb.DetectorType_Groq, | ||
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("Groq.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("Groq.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) | ||
} | ||
} | ||
}) | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -997,6 +997,7 @@ enum DetectorType { | |
Pagarme = 985; | ||
Onfleet = 986; | ||
Intra42 = 987; | ||
Groq = 988; | ||
} | ||
|
||
message Result { | ||
|