Merge branch 'main' into INS-170-Unify-JDBC-URL-parsing-across-detectors-and-analyzers

Author: mustansir14

CODEOWNERS

@@ -27,7 +27,7 @@ pkg/giturl/ @trufflesecurity/Scanning  @trufflesecurity/OSS
 pkg/handlers/ @trufflesecurity/Scanning  @trufflesecurity/OSS
 pkg/iobuf/ @trufflesecurity/Scanning  @trufflesecurity/OSS
 pkg/sanitizer/ @trufflesecurity/Scanning  @trufflesecurity/OSS
-proto/ @trufflesecurity/Scanning  @trufflesecurity/OSS
+proto/ @trufflesecurity/Scanning  @trufflesecurity/Integrations
 
 # OSS
 pkg/detectors/ @trufflesecurity/OSS

main.go

@@ -88,6 +88,7 @@ var (
 	// Add feature flags
 	forceSkipBinaries  = cli.Flag("force-skip-binaries", "Force skipping binaries.").Bool()
 	forceSkipArchives  = cli.Flag("force-skip-archives", "Force skipping archives.").Bool()
+	gitCloneTimeout    = cli.Flag("git-clone-timeout", "Maximum time to spend cloning a repository, as a duration.").Hidden().Duration()
 	skipAdditionalRefs = cli.Flag("skip-additional-refs", "Skip additional references.").Bool()
 	userAgentSuffix    = cli.Flag("user-agent-suffix", "Suffix to add to User-Agent.").String()
 
@@ -451,6 +452,10 @@ func run(state overseer.State) {
 		feature.ForceSkipArchives.Store(true)
 	}
 
+	if gitCloneTimeout != nil {
+		feature.GitCloneTimeoutDuration.Store(int64(*gitCloneTimeout))
+	}
+
 	if *skipAdditionalRefs {
 		feature.SkipAdditionalRefs.Store(true)
 	}

pkg/common/http.go

@@ -133,8 +133,8 @@ func (t *InstrumentedTransport) RoundTrip(req *http.Request) (*http.Response, er
 	}
 
 	if resp != nil {
-		// record latency and increment counter for non-200 status code
-		recordHTTPResponse(sanitizedURL, resp.StatusCode, duration.Seconds())
+		// record latency, response size and increment counter for non-200 status code
+		recordHTTPResponse(sanitizedURL, resp.StatusCode, duration.Seconds(), resp.ContentLength)
 	}
 
 	return resp, err
@@ -198,7 +198,7 @@ func WithRetryWaitMax(wait time.Duration) ClientOption {
 func PinnedRetryableHttpClient() *http.Client {
 	httpClient := retryablehttp.NewClient()
 	httpClient.Logger = nil
-	httpClient.HTTPClient.Transport = NewCustomTransport(&http.Transport{
+	httpClient.HTTPClient.Transport = NewInstrumentedTransport(NewCustomTransport(&http.Transport{
 		TLSClientConfig: &tls.Config{
 			RootCAs: PinnedCertPool(),
 		},
@@ -212,15 +212,15 @@ func PinnedRetryableHttpClient() *http.Client {
 		IdleConnTimeout:       90 * time.Second,
 		TLSHandshakeTimeout:   10 * time.Second,
 		ExpectContinueTimeout: 1 * time.Second,
-	})
+	}))
 	return httpClient.StandardClient()
 }
 
 func RetryableHTTPClient(opts ...ClientOption) *http.Client {
 	httpClient := retryablehttp.NewClient()
 	httpClient.RetryMax = 3
 	httpClient.Logger = nil
-	httpClient.HTTPClient.Transport = NewCustomTransport(nil)
+	httpClient.HTTPClient.Transport = NewInstrumentedTransport(NewCustomTransport(nil))
 
 	for _, opt := range opts {
 		opt(httpClient)
@@ -234,7 +234,7 @@ func RetryableHTTPClientTimeout(timeOutSeconds int64, opts ...ClientOption) *htt
 	httpClient.RetryMax = 3
 	httpClient.Logger = nil
 	httpClient.HTTPClient.Timeout = time.Duration(timeOutSeconds) * time.Second
-	httpClient.HTTPClient.Transport = NewCustomTransport(nil)
+	httpClient.HTTPClient.Transport = NewInstrumentedTransport(NewCustomTransport(nil))
 
 	for _, opt := range opts {
 		opt(httpClient)

pkg/common/http_metrics.go

@@ -39,6 +39,17 @@ var (
 		},
 		[]string{"url", "status_code"},
 	)
+
+	httpResponseBodySizeBytes = promauto.NewHistogramVec(
+		prometheus.HistogramOpts{
+			Namespace: MetricsNamespace,
+			Subsystem: "http_client",
+			Name:      "response_body_size_bytes",
+			Help:      "Size of HTTP response bodies in bytes, labeled by URL.",
+			Buckets:   prometheus.ExponentialBuckets(100, 10, 5), // [100B, 1KB, 10KB, 100KB, 1MB]
+		},
+		[]string{"url"},
+	)
 )
 
 // sanitizeURL sanitizes a URL to avoid high cardinality metrics.
@@ -92,14 +103,19 @@ func recordHTTPRequest(sanitizedURL string) {
 }
 
 // recordHTTPResponse records metrics for an HTTP response.
-func recordHTTPResponse(sanitizedURL string, statusCode int, durationSeconds float64) {
+func recordHTTPResponse(sanitizedURL string, statusCode int, durationSeconds float64, contentLength int64) {
 	// Record latency
 	httpRequestDuration.WithLabelValues(sanitizedURL).Observe(durationSeconds)
 
 	// Record non-200 responses
 	if statusCode != 200 {
 		httpNon200ResponsesTotal.WithLabelValues(sanitizedURL, strconv.Itoa(statusCode)).Inc()
 	}
+
+	// Record response body size if known
+	if contentLength >= 0 {
+		httpResponseBodySizeBytes.WithLabelValues(sanitizedURL).Observe(float64(contentLength))
+	}
 }
 
 // recordNetworkError records metrics for failed HTTP response

pkg/common/http_test.go

@@ -405,6 +405,73 @@ func TestSaneHttpClientMetrics(t *testing.T) {
 	}
 }
 
+func TestRetryableHttpClientMetrics(t *testing.T) {
+	// Create a test server that returns different status codes
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		switch r.URL.Path {
+		case "/success":
+			w.WriteHeader(http.StatusOK)
+			_, _ = w.Write([]byte("success"))
+		case "/error":
+			w.WriteHeader(http.StatusInternalServerError)
+			_, _ = w.Write([]byte("error"))
+		case "/notfound":
+			w.WriteHeader(http.StatusNotFound)
+			_, _ = w.Write([]byte("not found"))
+		default:
+			w.WriteHeader(http.StatusOK)
+			_, _ = w.Write([]byte("default"))
+		}
+	}))
+	defer server.Close()
+
+	// Create a RetryableHttpClient
+	client := RetryableHTTPClient()
+
+	testCases := []struct {
+		name               string
+		path               string
+		expectedStatusCode int
+	}{
+		{
+			name:               "successful request",
+			path:               "/success",
+			expectedStatusCode: 200,
+		},
+		{
+			name:               "not found request",
+			path:               "/notfound",
+			expectedStatusCode: 404,
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			var requestURL string
+			if strings.HasPrefix(tc.path, "http") {
+				requestURL = tc.path
+			} else {
+				requestURL = server.URL + tc.path
+			}
+
+			// Get initial metric values
+			sanitizedURL := sanitizeURL(requestURL)
+			initialRequestsTotal := testutil.ToFloat64(httpRequestsTotal.WithLabelValues(sanitizedURL))
+
+			// Make the request
+			resp, err := client.Get(requestURL)
+
+			require.NoError(t, err)
+			defer resp.Body.Close()
+			assert.Equal(t, tc.expectedStatusCode, resp.StatusCode)
+
+			// Check that request counter was incremented
+			requestsTotal := testutil.ToFloat64(httpRequestsTotal.WithLabelValues(sanitizedURL))
+			assert.Equal(t, initialRequestsTotal+1, requestsTotal)
+		})
+	}
+}
+
 func TestInstrumentedTransport(t *testing.T) {
 	// Create a mock transport that we can control
 	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {

pkg/detectors/copper/copper.go

@@ -2,6 +2,9 @@ package copper
 
 import (
 	"context"
+	"encoding/json"
+	"fmt"
+	"io"
 	"net/http"
 	"strings"
 
@@ -27,6 +30,11 @@ var (
 	idPat  = regexp.MustCompile(`\b([a-z0-9]{4,25}@[a-zA-Z0-9]{2,12}.[a-zA-Z0-9]{2,6})\b`)
 )
 
+type UserApiResponse struct {
+	Id    int    `json:"id"`
+	Email string `json:"email"`
+}
+
 // Keywords are used for efficiently pre-filtering chunks.
 // Use identifiers in the secret preferably, or the provider name.
 func (s Scanner) Keywords() []string {
@@ -52,26 +60,9 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 			}
 
 			if verify {
-
-				payload := strings.NewReader(`{
-					"page_size": 25,
-					"sort_by": "name"
-					}`)
-				req, err := http.NewRequestWithContext(ctx, "POST", "https://api.copper.com/developer_api/v1/tasks/search", payload)
-				if err != nil {
-					continue
-				}
-				req.Header.Add("X-PW-AccessToken", resMatch)
-				req.Header.Add("X-PW-Application", "developer_api")
-				req.Header.Add("X-PW-UserEmail", resIdMatch)
-				req.Header.Add("Content-Type", "application/json")
-				res, err := client.Do(req)
-				if err == nil {
-					defer res.Body.Close()
-					if res.StatusCode >= 200 && res.StatusCode < 300 {
-						s1.Verified = true
-					}
-				}
+				isVerified, verificationErr := verifyCopper(ctx, client, resIdMatch, resMatch)
+				s1.Verified = isVerified
+				s1.SetVerificationError(verificationErr, resMatch)
 			}
 
 			results = append(results, s1)
@@ -83,6 +74,54 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 	return results, nil
 }
 
+func verifyCopper(ctx context.Context, client *http.Client, email, apiKey string) (bool, error) {
+	req, err := http.NewRequestWithContext(
+		ctx,
+		http.MethodGet,
+		"https://api.copper.com/developer_api/v1/users/me",
+		http.NoBody,
+	)
+	if err != nil {
+		return false, err
+	}
+	req.Header.Add("X-PW-AccessToken", apiKey)
+	req.Header.Add("X-PW-Application", "developer_api")
+	req.Header.Add("X-PW-UserEmail", email)
+	req.Header.Add("Content-Type", "application/json")
+	res, err := client.Do(req)
+	if err != nil {
+		return false, err
+	}
+	defer func() {
+		_, _ = io.Copy(io.Discard, res.Body)
+		_ = res.Body.Close()
+	}()
+
+	switch res.StatusCode {
+	case http.StatusOK:
+		respBytes, err := io.ReadAll(res.Body)
+		if err != nil {
+			return false, err
+		}
+
+		var respBody UserApiResponse
+		if err := json.Unmarshal(respBytes, &respBody); err != nil {
+			return false, err
+		}
+
+		// strict verification with email in credentials
+		if respBody.Email == email {
+			return true, nil
+		}
+
+		return false, fmt.Errorf("email mismatch in verification response")
+	case http.StatusUnauthorized:
+		return false, nil
+	default:
+		return false, fmt.Errorf("unexpected status code :%d", res.StatusCode)
+	}
+}
+
 func (s Scanner) Type() detectorspb.DetectorType {
 	return detectorspb.DetectorType_Copper
 }

pkg/detectors/copper/copper_integration_test.go

@@ -9,8 +9,8 @@ import (
 	"testing"
 	"time"
 
-	"github.com/kylelemons/godebug/pretty"
-
+	"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"
@@ -96,9 +96,11 @@ func TestCopper_FromChunk(t *testing.T) {
 					t.Fatalf("no raw secret present: \n %+v", got[i])
 				}
 				got[i].Raw = nil
+				got[i].RawV2 = nil
 			}
-			if diff := pretty.Compare(got, tt.want); diff != "" {
-				t.Errorf("Copper.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError", "primarySecret")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Abstract.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
 			}
 		})
 	}

pkg/detectors/ftp/ftp.go

@@ -78,8 +78,15 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
 		}
 
 		if verify {
-			timeout := s.verificationTimeout
-			if timeout == 0 {
+			var timeout time.Duration
+			if s.verificationTimeout > 0 {
+				// Use to configure a simulate timeout for interation tests
+				timeout = s.verificationTimeout
+			} else if dl, ok := ctx.Deadline(); ok {
+				// Here we assign the remaining time before our context expires
+				// This help us cater the timelimit set through --detector-timeout flag
+				timeout = time.Until(dl)
+			} else {
 				timeout = defaultVerificationTimeout
 			}
 			verificationErr := verifyFTP(timeout, parsedURL)
@@ -126,6 +133,9 @@ func verifyFTP(timeout time.Duration, u *url.URL) error {
 		return err
 	}
 
+	defer func() {
+		_ = c.Quit()
+	}()
 	password, _ := u.User.Password()
 	return c.Login(u.User.Username(), password)
 }

pkg/detectors/ftp/ftp_integration_test.go

@@ -149,7 +149,7 @@ func TestFTP_FromChunk(t *testing.T) {
 					t.Fatalf("wantVerificationError = %v, verification error = %v", tt.wantVerificationErr, got[i].VerificationError())
 				}
 			}
-			opts := cmpopts.IgnoreFields(detectors.Result{}, "verificationError")
+			opts := cmpopts.IgnoreFields(detectors.Result{}, "verificationError", "primarySecret")
 			if diff := cmp.Diff(got, tt.want, opts); diff != "" {
 				t.Errorf("FTP.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
 			}