feat(azure): update sp detector

pkg/detectors/azure_entra/serviceprincipal/sp.go

@@ -0,0 +1,116 @@
+package serviceprincipal
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"strconv"
+	"strings"
+
+	"github.com/golang-jwt/jwt/v5"
+)
+
+var (
+	ErrSecretInvalid          = errors.New("invalid client secret provided")
+	ErrSecretExpired          = errors.New("the provided secret is expired")
+	ErrTenantNotFound         = errors.New("tenant not found")
+	ErrClientNotFoundInTenant = errors.New("application was not found in tenant")
+)
+
+type TokenOkResponse struct {
+	AccessToken string `json:"access_token"`
+}
+
+type TokenErrResponse struct {
+	Error       string `json:"error"`
+	Description string `json:"error_description"`
+}
+
+// VerifyCredentials attempts to get a token using the provided client credentials.
+// See: https://learn.microsoft.com/en-us/entra/identity-platform/v2-oauth2-client-creds-grant-flow#get-a-token
+func VerifyCredentials(ctx context.Context, client *http.Client, tenantId string, clientId string, clientSecret string) (bool, map[string]string, error) {
+	data := url.Values{}
+	data.Set("client_id", clientId)
+	//data.Set("scope", "https://management.core.windows.net/.default")
+	data.Set("scope", "https://graph.microsoft.com/.default")
+	data.Set("client_secret", clientSecret)
+	data.Set("grant_type", "client_credentials")
+
+	tokenUrl := fmt.Sprintf("https://login.microsoftonline.com/%s/oauth2/v2.0/token", tenantId)
+	encodedData := data.Encode()
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, tokenUrl, strings.NewReader(encodedData))
+	if err != nil {
+		return false, nil, nil
+	}
+	req.Header.Set("Accept", "application/json")
+	req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
+	req.Header.Set("Content-Length", strconv.Itoa(len(encodedData)))
+
+	res, err := client.Do(req)
+	if err != nil {
+		return false, nil, err
+	}
+	defer func() {
+		_, _ = io.Copy(io.Discard, res.Body)
+		_ = res.Body.Close()
+	}()
+
+	if res.StatusCode == http.StatusOK {
+		var okResp TokenOkResponse
+
+		if err := json.NewDecoder(res.Body).Decode(&okResp); err != nil {
+			return false, nil, err
+		}
+
+		extraData := map[string]string{
+			"rotation_guide": "https://howtorotate.com/docs/tutorials/azure/",
+			"tenant":         tenantId,
+			"client":         clientId,
+		}
+
+		// Add claims from the access token.
+		if token, _ := jwt.Parse(okResp.AccessToken, nil); token != nil {
+			claims := token.Claims.(jwt.MapClaims)
+
+			if app := claims["app_displayname"]; app != nil {
+				extraData["application"] = fmt.Sprint(app)
+			}
+		}
+		return true, extraData, nil
+	} else {
+		var errResp TokenErrResponse
+		if err := json.NewDecoder(res.Body).Decode(&errResp); err != nil {
+			return false, nil, err
+		}
+
+		switch res.StatusCode {
+		case http.StatusBadRequest, http.StatusUnauthorized:
+			// Error codes can be looked up by removing the `AADSTS` prefix.
+			// https://login.microsoftonline.com/error?code=9002313
+			d := errResp.Description
+			switch {
+			case strings.HasPrefix(d, "AADSTS700016:"):
+				// https://login.microsoftonline.com/error?code=700016
+				return false, nil, ErrClientNotFoundInTenant
+			case strings.HasPrefix(d, "AADSTS7000215:"):
+				// https://login.microsoftonline.com/error?code=7000215
+				return false, nil, ErrSecretInvalid
+			case strings.HasPrefix(d, "AADSTS7000222:"):
+				// The secret has expired.
+				// https://login.microsoftonline.com/error?code=7000222
+				return false, nil, ErrSecretExpired
+			case strings.HasPrefix(d, "AADSTS90002:"):
+				// https://login.microsoftonline.com/error?code=90002
+				return false, nil, ErrTenantNotFound
+			default:
+				return false, nil, fmt.Errorf("unexpected error '%s': %s", errResp.Error, errResp.Description)
+			}
+		default:
+			return false, nil, fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
+		}
+	}
+}

pkg/detectors/azure_entra/serviceprincipal/v1/spv1.go

@@ -0,0 +1,89 @@
+package v1
+
+import (
+	"context"
+	"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/detectors/azure_entra"
+	v2 "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/azure_entra/serviceprincipal/v2"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
+)
+
+type Scanner struct {
+	client *http.Client
+	detectors.DefaultMultiPartCredentialProvider
+}
+
+// Ensure the Scanner satisfies the interface at compile time.
+var _ interface {
+	detectors.Detector
+	detectors.Versioner
+} = (*Scanner)(nil)
+
+var (
+	defaultClient = common.SaneHttpClient()
+	// TODO: Azure storage access keys and investigate other types of creds.
+	// https://learn.microsoft.com/en-us/entra/identity-platform/v2-oauth2-client-creds-grant-flow#second-case-access-token-request-with-a-certificate
+	// https://learn.microsoft.com/en-us/entra/identity-platform/v2-oauth2-client-creds-grant-flow#third-case-access-token-request-with-a-federated-credential
+	//clientSecretPat = regexp.MustCompile(`(?i)(?:secret|password| -p[ =]).{0,40}?([a-z0-9~@_\-[\]:.?]{32,34})`)
+	secretPat = regexp.MustCompile(`(?i)(?:secret|password| -p[ =]).{0,80}[^A-Za-z0-9!#$%&()*+,\-./:;<=>?@[\\\]^_{|}~]([A-Za-z0-9!#$%&()*+,\-./:;<=>?@[\\\]^_{|}~]{31,34})[^A-Za-z0-9!#$%&()*+,\-./:;<=>?@[\\\]^_{|}~]`)
+)
+
+func (s Scanner) Version() int {
+	return 1
+}
+
+// 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{"azure", "az", "entra", "msal", "login.microsoftonline.com", ".onmicrosoft.com"}
+}
+
+// FromData will find and optionally verify Azure 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)
+
+	clientSecrets := findSecretMatches(dataStr)
+	if len(clientSecrets) == 0 {
+		return
+	}
+	clientIds := azure_entra.FindClientIdMatches(dataStr)
+	if len(clientIds) == 0 {
+		return
+	}
+	tenantIds := azure_entra.FindTenantIdMatches(dataStr)
+
+	client := s.client
+	if client == nil {
+		client = defaultClient
+	}
+	processedResults := v2.ProcessData(ctx, clientSecrets, clientIds, tenantIds, verify, client)
+	for _, result := range processedResults {
+		results = append(results, result)
+	}
+	return results, nil
+}
+
+func (s Scanner) Type() detectorspb.DetectorType {
+	return detectorspb.DetectorType_Azure
+}
+
+// region Helper methods.
+func findSecretMatches(data string) map[string]struct{} {
+	uniqueMatches := make(map[string]struct{})
+	for _, match := range secretPat.FindAllStringSubmatch(data, -1) {
+		m := match[1]
+		// Ignore secrets that are handled by the V2 detector.
+		if v2.SecretPat.MatchString(m) {
+			continue
+		}
+		uniqueMatches[m] = struct{}{}
+	}
+	return uniqueMatches
+}
+
+//endregion

pkg/detectors/azure_entra/serviceprincipal/serviceprincipal_test.go → pkg/detectors/azure_entra/serviceprincipal/v1/spv1_integration_test.go

@@ -1,7 +1,7 @@
 //go:build detectors
 // +build detectors
 
-package azure_entra_serviceprincipal
+package v1
 
 import (
 	"context"