Update artifactory detector with basic auth support

pkg/detectors/artifactory/artifactory.go → pkg/detectors/artifactory/accesstoken/artifactoryaccesstoken.go

@@ -37,6 +37,7 @@ var (
 	errNoHost = errors.New("no such host")
 )
 
+
 func (Scanner) CloudEndpoint() string { return "" }
 
 // Keywords are used for efficiently pre-filtering chunks.

pkg/detectors/artifactory/basicauth/artifactorybasicauth.go

@@ -0,0 +1,211 @@
+package artifactory
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+
+	regexp "github.com/wasilibs/go-re2"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/cache/simple"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+type Scanner struct {
+	client *http.Client
+	detectors.DefaultMultiPartCredentialProvider
+}
+
+type basicArtifactoryCredential struct {
+	username string
+	password string
+	host     string
+	raw      string
+}
+
+var (
+	// Ensure the Scanner satisfies the interface at compile time.
+	_ detectors.Detector           = (*Scanner)(nil)
+	_ detectors.CustomFalsePositiveChecker = (*Scanner)(nil)
+
+	defaultClient = detectors.DetectorHttpClientWithNoLocalAddresses
+
+	basicAuthURLPattern = regexp.MustCompile(
+		`(?P<username>[^:@\s\/]+):(?P<password>[^:@\s\/]+)@(?P<host>[A-Za-z0-9][A-Za-z0-9\-]{0,61}[A-Za-z0-9]\.jfrog\.io)(?P<path>/[^\s"'<>]*)?`,
+	)
+
+	invalidHosts = simple.NewCache[struct{}]()
+
+	errNoHost = errors.New("no such host")
+)
+
+
+// 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{"artifactory", "jfrog.io"}
+}
+
+func (s Scanner) getClient() *http.Client {
+	if s.client != nil {
+		return s.client
+	}
+	return defaultClient
+}
+
+// FromData will find and optionally verify Artifactory 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)
+
+	// ----------------------------------------
+	// Basic Auth URI detection & verification
+	// ----------------------------------------
+	basicCreds := make(map[string]basicArtifactoryCredential)
+
+	for _, match := range basicAuthURLPattern.FindAllStringSubmatch(dataStr, -1) {
+		if len(match) == 0 {
+			continue
+		}
+		subexpNames := basicAuthURLPattern.SubexpNames()
+
+		var username, password, host string
+		for i, name := range subexpNames {
+			if i == 0 || name == "" {
+				continue
+			}
+			switch name {
+			case "username":
+				username = match[i]
+			case "password":
+				password = match[i]
+			case "host":
+				host = match[i]
+			}
+		}
+
+		if username == "" || password == "" || host == "" {
+			continue
+		}
+
+		key := username + ":" + password + "@" + host
+		if _, exists := basicCreds[key]; exists {
+			continue
+		}
+
+		basicCreds[key] = basicArtifactoryCredential{
+			username: username,
+			password: password,
+			host:     host,
+			raw:      match[0],
+		}
+	}
+
+	for _, cred := range basicCreds {
+		if invalidHosts.Exists(cred.host) {
+			continue
+		}
+
+		r := detectors.Result{
+			DetectorType: detectorspb.DetectorType_ArtifactoryBasicAuth,
+			Raw:          []byte(cred.raw),
+			RawV2:        []byte(cred.username + ":" + cred.password + "@" + cred.host),
+		}
+
+		if verify {
+			isVerified, vErr := verifyArtifactoryBasicAuth(ctx, s.getClient(), cred.host, cred.username, cred.password)
+			r.Verified = isVerified
+
+			if vErr != nil {
+				if errors.Is(vErr, errNoHost) {
+					invalidHosts.Set(cred.host, struct{}{})
+					continue
+				}
+				r.SetVerificationError(vErr, cred.username, cred.password)
+			}
+
+			if isVerified {
+				if r.AnalysisInfo == nil {
+					r.AnalysisInfo = make(map[string]string)
+				}
+				r.AnalysisInfo["domain"] = cred.host
+				r.AnalysisInfo["username"] = cred.username
+				r.AnalysisInfo["password"] = cred.password
+				r.AnalysisInfo["authType"] = "basic"
+			}
+		}
+
+		results = append(results, r)
+	}
+
+	return results, nil
+}
+
+func (s Scanner) IsFalsePositive(_ detectors.Result) (bool, string) {
+	return false, ""
+}
+
+func verifyArtifactoryBasicAuth(ctx context.Context, client *http.Client, host, username, password string) (bool, error) {
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, "https://"+host+"/artifactory/api/system/ping", nil)
+	if err != nil {
+		return false, err
+	}
+
+	// Use HTTP Basic authentication with the parsed username and password.
+	req.SetBasicAuth(username, password)
+
+	resp, err := client.Do(req)
+	if err != nil {
+		if strings.Contains(err.Error(), "no such host") {
+			return false, errNoHost
+		}
+
+		return false, err
+	}
+
+	defer func() {
+		_, _ = io.Copy(io.Discard, resp.Body)
+		_ = resp.Body.Close()
+	}()
+
+	switch resp.StatusCode {
+	case http.StatusOK:
+		body, err := io.ReadAll(resp.Body)
+		if err != nil {
+			return false, err
+		}
+
+        if strings.TrimSpace(string(body)) == "OK" {
+            return true, nil
+        }
+
+		return false, nil
+	case http.StatusForbidden:
+        body, err := io.ReadAll(resp.Body)
+        if err != nil {
+            return false, err
+        }
+
+        // Ignore rate-limit / temporary block 403s
+        if strings.Contains(strings.ToLower(string(body)), "blocked due to recurrent request failures") {
+            return false, nil
+        }
+
+        return true, nil
+	case http.StatusUnauthorized, http.StatusFound:
+		return false, nil
+	default:
+		return false, fmt.Errorf("unexpected HTTP response status %d", resp.StatusCode)
+	}
+}
+
+func (s Scanner) Type() detectorspb.DetectorType {
+	return detectorspb.DetectorType_ArtifactoryBasicAuth
+}
+
+func (s Scanner) Description() string {
+	return "Artifactory is a repository manager that supports all major package formats. Artifactory Basic Auth credentials can be used to authenticate and perform operations on repositories."
+}

pkg/detectors/artifactory/basicauth/artifactorybasicauth_integration_test.go

@@ -0,0 +1,146 @@
+//go:build detectors
+// +build detectors
+
+package artifactory
+
+import (
+	"context"
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+func TestArtifactory_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)
+	}
+	basicAuthValid := testSecrets.MustGetField("ARTIFACTORY_BASIC_AUTH_VALID")
+	basicAuthInactive := testSecrets.MustGetField("ARTIFACTORY_BASIC_AUTH_INACTIVE")
+
+	type args struct {
+		ctx    context.Context
+		data   []byte
+		verify bool
+	}
+	tests := []struct {
+		name    string
+		s       Scanner
+		args    args
+		want    []detectors.Result
+		wantErr bool
+	}{
+		{
+			name: "found, verified",
+			s:    Scanner{},
+			args: args{
+				ctx: context.Background(),
+				data: []byte(fmt.Sprintf(
+					"You can find an Artifactory basic auth URL https://%s/artifactory/api/pypi/pypi/simple",
+					basicAuthValid,
+				)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_ArtifactoryBasicAuth,
+					Verified:     true,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "found, unverified",
+			s:    Scanner{},
+			args: args{
+				ctx: context.Background(),
+				data: []byte(fmt.Sprintf(
+					"You can find an Artifactory basic auth URL https://%s/artifactory/api/pypi/pypi/simple but it's not valid",
+					basicAuthInactive,
+				)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_ArtifactoryBasicAuth,
+					Verified:     false,
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "not found",
+			s:    Scanner{},
+			args: args{
+				ctx:    context.Background(),
+				data:   []byte("You cannot find any Artifactory basic auth URL within this chunk"),
+				verify: true,
+			},
+			want:    nil,
+			wantErr: false,
+		},
+	}
+	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("Artifactory.FromData() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+
+			if len(tt.want) == 0 {
+				if len(got) != 0 {
+					t.Fatalf("expected no results, got %d", len(got))
+				}
+				return
+			}
+
+			for i := range got {
+				if len(got[i].Raw) == 0 && len(got[i].RawV2) == 0 {
+					t.Fatalf("no raw secret present: \n %+v", got[i])
+				}
+				gotErr := ""
+				if got[i].VerificationError() != nil {
+					gotErr = got[i].VerificationError().Error()
+				}
+				wantErr := ""
+				if tt.want[i].VerificationError() != nil {
+					wantErr = tt.want[i].VerificationError().Error()
+				}
+				if gotErr != wantErr {
+					t.Fatalf("wantVerificationError = %v, verification error = %v",
+						tt.want[i].VerificationError(), got[i].VerificationError())
+				}
+			}
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError", "primarySecret")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Artifactory.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)
+				}
+			}
+		})
+	}
+}