Okta Detector - Added Check for Indeterminate Verification Results (#4045)

* updated okta detector; add indeterminate verification error return

* refactored, added adjustable client, updated integration test to include verification error test

Author: nabeelalam

pkg/detectors/okta/okta.go

@@ -3,26 +3,26 @@ package okta
 import (
 	"context"
 	"fmt"
-	"io"
 	"net/http"
-	"strings"
 
 	regexp "github.com/wasilibs/go-re2"
 
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
 )
 
-type Scanner struct{
+type Scanner struct {
+	client *http.Client
 	detectors.DefaultMultiPartCredentialProvider
 }
 
 // Ensure the Scanner satisfies the interface at compile time.
 var _ detectors.Detector = (*Scanner)(nil)
 
 var (
-	domainPat = regexp.MustCompile(`\b[a-z0-9-]{1,40}\.okta(?:preview|-emea){0,1}\.com\b`)
-	tokenPat  = regexp.MustCompile(`\b00[a-zA-Z0-9_-]{40}\b`)
+	defaultClient = detectors.DetectorHttpClientWithNoLocalAddresses
+	domainPat     = regexp.MustCompile(`\b[a-z0-9-]{1,40}\.okta(?:preview|-emea){0,1}\.com\b`)
+	tokenPat      = regexp.MustCompile(`\b00[a-zA-Z0-9_-]{40}\b`)
 	// TODO: Oauth client secrets
 )
 
@@ -34,55 +34,76 @@ func (s Scanner) Keywords() []string {
 
 // FromData will find and optionally verify Okta secrets in a given set of bytes.
 func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
-	for _, tokenMatch := range tokenPat.FindAll(data, -1) {
-		token := string(tokenMatch)
+	dataStr := string(data)
 
-		for _, domainMatch := range domainPat.FindAll(data, -1) {
-			domain := string(domainMatch)
+	var uniqueTokens, uniqueDomains = make(map[string]struct{}), make(map[string]struct{})
 
-			result := detectors.Result{
+	for _, matches := range tokenPat.FindAllStringSubmatch(dataStr, -1) {
+		uniqueTokens[matches[0]] = struct{}{}
+	}
+
+	for _, matches := range domainPat.FindAllStringSubmatch(dataStr, -1) {
+		uniqueDomains[matches[0]] = struct{}{}
+	}
+
+	for token := range uniqueTokens {
+		for domain := range uniqueDomains {
+			s1 := detectors.Result{
 				DetectorType: detectorspb.DetectorType_Okta,
 				Raw:          []byte(token),
 				RawV2:        []byte(fmt.Sprintf("%s:%s", domain, token)),
 			}
 
 			if verify {
-				// curl -v -X GET \
-				// -H "Accept: application/json" \
-				// -H "Content-Type: application/json" \
-				// -H "Authorization: Bearer token" \
-				// "https://subdomain.okta.com/api/v1/users/me"
-				//
-
-				url := fmt.Sprintf("https://%s/api/v1/users/me", domain)
-				req, err := http.NewRequestWithContext(ctx, "GET", url, nil)
-				if err != nil {
-					return results, err
+				client := s.client
+				if client == nil {
+					client = defaultClient
 				}
-				req.Header.Set("Accept", "application/json")
-				req.Header.Set("Content-Type", "application/json")
-				req.Header.Set("Authorization", fmt.Sprintf("SSWS %s", token))
 
-				resp, err := detectors.DetectorHttpClientWithNoLocalAddresses.Do(req)
-				if err != nil {
-					continue
-				}
-				defer resp.Body.Close()
-				if resp.StatusCode >= 200 && resp.StatusCode < 300 {
-					body, _ := io.ReadAll(resp.Body)
-					if strings.Contains(string(body), "activated") {
-						result.Verified = true
-					}
-				}
+				isVerified, verificationErr := verifyOktaToken(ctx, client, domain, token)
+				s1.Verified = isVerified
+				s1.SetVerificationError(verificationErr)
 			}
 
-			results = append(results, result)
+			results = append(results, s1)
 		}
 	}
 
 	return
 }
 
+func verifyOktaToken(ctx context.Context, client *http.Client, domain string, token string) (bool, error) {
+	// curl -v -X GET \
+	// -H "Accept: application/json" \
+	// -H "Content-Type: application/json" \
+	// -H "Authorization: SSWS token" \
+	// "https://subdomain.okta.com/api/v1/users/me"
+
+	url := fmt.Sprintf("https://%s/api/v1/users/me", domain)
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+	if err != nil {
+		return false, err
+	}
+	req.Header.Set("Accept", "application/json")
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Authorization", fmt.Sprintf("SSWS %s", token))
+
+	resp, err := client.Do(req)
+	if err != nil {
+		return false, err
+	}
+	defer resp.Body.Close()
+
+	switch resp.StatusCode {
+	case http.StatusOK:
+		return true, nil
+	case http.StatusUnauthorized, http.StatusForbidden:
+		return false, nil
+	default:
+		return false, fmt.Errorf("unexpected status code: %d", resp.StatusCode)
+	}
+}
+
 func (s Scanner) Type() detectorspb.DetectorType {
 	return detectorspb.DetectorType_Okta
 }

pkg/detectors/okta/okta_integration_test.go

@@ -9,7 +9,9 @@ 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"
@@ -32,11 +34,12 @@ func TestOkta_FromChunk(t *testing.T) {
 		verify bool
 	}
 	tests := []struct {
-		name    string
-		s       Scanner
-		args    args
-		want    []detectors.Result
-		wantErr bool
+		name                string
+		s                   Scanner
+		args                args
+		want                []detectors.Result
+		wantErr             bool
+		wantVerificationErr bool
 	}{
 		{
 			name: "found token, verified",
@@ -52,7 +55,8 @@ func TestOkta_FromChunk(t *testing.T) {
 					Verified:     true,
 				},
 			},
-			wantErr: false,
+			wantErr:             false,
+			wantVerificationErr: false,
 		},
 		{
 			name: "found, unverified",
@@ -68,7 +72,8 @@ func TestOkta_FromChunk(t *testing.T) {
 					Verified:     false,
 				},
 			},
-			wantErr: false,
+			wantErr:             false,
+			wantVerificationErr: false,
 		},
 		{
 			name: "not found",
@@ -78,26 +83,46 @@ func TestOkta_FromChunk(t *testing.T) {
 				data:   []byte("You cannot find the secret within"),
 				verify: true,
 			},
-			want:    nil,
-			wantErr: false,
+			want:                nil,
+			wantErr:             false,
+			wantVerificationErr: false,
+		},
+		{
+			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 okta secret %s within oktaDomain %s", secretInactive, domain)),
+				verify: true,
+			},
+			want: []detectors.Result{
+				{
+					DetectorType: detectorspb.DetectorType_Okta,
+					Verified:     false,
+				},
+			},
+			wantErr:             false,
+			wantVerificationErr: true,
 		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			s := Scanner{}
-			got, err := s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
+			got, err := tt.s.FromData(tt.args.ctx, tt.args.verify, tt.args.data)
 			if (err != nil) != tt.wantErr {
 				t.Errorf("Okta.FromData) error = %v, wantErr %v", err, tt.wantErr)
 				return
 			}
 			for i := range got {
 				if len(got[i].Raw) == 0 {
-					t.Fatal("no raw secret present")
+					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())
 				}
-				got[i].Raw = nil
 			}
-			if diff := pretty.Compare(got, tt.want); diff != "" {
-				t.Errorf("Okta.FromData) %s diff: (-got +want)\n%s", tt.name, diff)
+			ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "Raw", "RawV2", "verificationError")
+			if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" {
+				t.Errorf("Okta.FromData() %s diff: (-got +want)\n%s", tt.name, diff)
 			}
 		})
 	}