modified Alibaba detector to use standard library (#568)

* added alibaba detector * enhancement * enhancement and ran mod tidy * fixed
2022-05-23 18:37:01 -07:00
parent 66dc7efac0
commit da872f5c27
4 changed files with 105 additions and 60 deletions
@@ -9,7 +9,6 @@ replace github.com/zricethezav/gitleaks/v8 => github.com/trufflesecurity/gitleak
 require (
 	cloud.google.com/go/secretmanager v1.4.0
 	github.com/Azure/go-autorest/autorest/azure/auth v0.5.11
-	github.com/aliyun/alibaba-cloud-sdk-go v1.61.1465
 	github.com/aws/aws-sdk-go v1.44.9
 	github.com/aws/aws-sdk-go-v2/credentials v1.12.0
 	github.com/aws/aws-sdk-go-v2/service/sts v1.16.4
@@ -93,12 +92,9 @@ require (
 	github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
 	github.com/jmespath/go-jmespath v0.4.0 // indirect
 	github.com/jpillora/s3 v1.1.4 // indirect
-	github.com/json-iterator/go v1.1.11 // indirect
 	github.com/kevinburke/ssh_config v0.0.0-20201106050909-4977a11b4351 // indirect
 	github.com/mattn/go-isatty v0.0.14 // indirect
 	github.com/mitchellh/go-homedir v1.1.0 // indirect
-	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
-	github.com/modern-go/reflect2 v1.0.1 // indirect
 	github.com/pkg/diff v0.0.0-20200914180035-5b29258ca4f7 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/xanzy/ssh-agent v0.3.0 // indirect
@@ -113,7 +109,6 @@ require (
 	google.golang.org/api v0.74.0 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
 	google.golang.org/grpc v1.45.0 // indirect
-	gopkg.in/ini.v1 v1.66.2 // indirect
 	gopkg.in/warnings.v0 v0.1.2 // indirect
 	gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b // indirect
 )
@@ -87,8 +87,6 @@ github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751 h1:JYp7IbQjafo
 github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
 github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 h1:s6gZFSlWYmbqAuRjVTiNNhvNRfY2Wxp9nhfyel4rklc=
 github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137/go.mod h1:OMCwj8VM1Kc9e19TLln2VL61YJF0x1XFtfdL4JdbSyE=
-github.com/aliyun/alibaba-cloud-sdk-go v1.61.1465 h1:8i+XtPz4IuZEM6biUBnfQbKdJPKek9/QaPEbRCfnIBw=
-github.com/aliyun/alibaba-cloud-sdk-go v1.61.1465/go.mod h1:RcDobYh8k5VP6TNybz9m++gL3ijVI5wueVr0EM10VsU=
 github.com/anmitsu/go-shlex v0.0.0-20161002113705-648efa622239 h1:kFOfPq6dUM1hTo4JG6LR5AXSUEsOjtdm0kw0FtQtMJA=
 github.com/anmitsu/go-shlex v0.0.0-20161002113705-648efa622239/go.mod h1:2FmKhYUyUczH0OGQWaF5ceTx0UBShxjsH6f8oGKYe2c=
 github.com/antihax/optional v1.0.0/go.mod h1:uupD/76wgC+ih3iEmQUL+0Ugr19nfwCT1kdvxnR2qWY=
@@ -198,7 +196,6 @@ github.com/gobwas/pool v0.2.1/go.mod h1:q8bcK0KcYlCgd9e7WYLm9LpyS+YeLd8JVDW6Wezm
 github.com/gobwas/ws v1.0.4/go.mod h1:szmBTxLgaFppYjEmNtny/v3w89xOydFnnZMcgRRu/EM=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
-github.com/goji/httpauth v0.0.0-20160601135302-2da839ab0f4d/go.mod h1:nnjvkQ9ptGaCkuDUx6wNykzzlUixGxvkme+H/lnzb+A=
 github.com/golang-jwt/jwt v3.2.2+incompatible h1:IfV12K8xAKAnZqdXVzCZ+TOjboZ2keLg81eXfW3O+oY=
 github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzqecmYZeUEB8OUGHkxJ+I=
 github.com/golang-jwt/jwt/v4 v4.0.0/go.mod h1:/xlHOz8bRuivTWchD4jCa+NbatV+wEUSzwAxVc6locg=
@@ -334,7 +331,6 @@ github.com/inconshreveable/mousetrap v1.0.0/go.mod h1:PxqpIevigyE2G7u3NXJIT2ANyt
 github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A=
 github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99/go.mod h1:1lJo3i6rXxKeerYnT8Nvf0QmHCRC1n8sfWVwXF2Frvo=
 github.com/jessevdk/go-flags v1.5.0/go.mod h1:Fw0T6WPc1dYxT4mKEZRfG5kJhaTDP9pj1c2EWnYs/m4=
-github.com/jmespath/go-jmespath v0.0.0-20180206201540-c2b33e8439af/go.mod h1:Nht3zPeWKUH0NzdCt2Blrr5ys8VGpn0CEB0cQHVjt7k=
 github.com/jmespath/go-jmespath v0.4.0 h1:BEgLn5cpjn8UN1mAw4NjwDrS35OdebyEtFe+9YPoQUg=
 github.com/jmespath/go-jmespath v0.4.0/go.mod h1:T8mJZnbsbmF+m6zOOFylbeCJqk5+pHWvzYPziyZiYoo=
 github.com/jmespath/go-jmespath/internal/testify v1.5.1 h1:shLQSRRSCCPj3f2gpwzGwWFoC7ycTf1rcQZHOlsJ6N8=
@@ -343,8 +339,6 @@ github.com/joho/godotenv v1.4.0 h1:3l4+N6zfMWnkbPEXKng2o2/MR5mSwTrBih4ZEkkz1lg=
 github.com/joho/godotenv v1.4.0/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
 github.com/jpillora/s3 v1.1.4 h1:YCCKDWzb/Ye9EBNd83ATRF/8wPEy0xd43Rezb6u6fzc=
 github.com/jpillora/s3 v1.1.4/go.mod h1:yedE603V+crlFi1Kl/5vZJaBu9pUzE9wvKegU/lF2zs=
-github.com/json-iterator/go v1.1.5/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
-github.com/json-iterator/go v1.1.11 h1:uVUAXhF2To8cbw/3xN3pxj6kk7TYKs98NIrTqPlMWAQ=
 github.com/json-iterator/go v1.1.11/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/jstemmer/go-junit-report v0.0.0-20190106144839-af01ea7f8024/go.mod h1:6v2b51hI/fHJwM22ozAgKL4VKDeJcHhJFhtBdhmNjmU=
 github.com/jstemmer/go-junit-report v0.9.1/go.mod h1:Brl9GWCQeLvo8nXZwPNNblvFj/XSXhF0NWZEnDohbsk=
@@ -388,10 +382,7 @@ github.com/mitchellh/mapstructure v0.0.0-20160808181253-ca63d7c062ee/go.mod h1:F
 github.com/mitchellh/mapstructure v1.1.2/go.mod h1:FVVH3fgwuzCH5S8UJGiWEs2h04kUh9fWfEaFds41c1Y=
 github.com/mitchellh/mapstructure v1.4.1/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
-github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
-github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
-github.com/modern-go/reflect2 v1.0.1 h1:9f412s+6RmYXLWZSEzVVgPGK7C2PphHj5RJrvfx9AWI=
 github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/nbio/st v0.0.0-20140626010706-e9e8d9816f32 h1:W6apQkHrMkS0Muv8G/TipAy/FJl/rCYT0+EuS8+Z0z4=
 github.com/nbio/st v0.0.0-20140626010706-e9e8d9816f32/go.mod h1:9wM+0iRr9ahx58uYLpLIr5fm8diHn0JbqRycJi6w0Ms=
@@ -938,8 +929,6 @@ gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
 gopkg.in/h2non/gock.v1 v1.1.2 h1:jBbHXgGBK/AoPVfJh5x4r/WxIrElvbLel8TCZkkZJoY=
 gopkg.in/h2non/gock.v1 v1.1.2/go.mod h1:n7UGz/ckNChHiK05rDoiC4MYSunEC/lyaUm2WWaDva0=
 gopkg.in/ini.v1 v1.62.0/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
-gopkg.in/ini.v1 v1.66.2 h1:XfR1dOYubytKy4Shzc2LHrrGhU0lDCfDGG1yLPmpgsI=
-gopkg.in/ini.v1 v1.66.2/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
 gopkg.in/warnings.v0 v0.1.2 h1:wFXVbFY8DY5/xOe1ECiWdKCzZlxgshcYVNkBHstARME=
 gopkg.in/warnings.v0 v0.1.2/go.mod h1:jksf8JmL6Qr/oQM2OXTHunEvvTAsrWBLb6OOjuVWRNI=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
@@ -2,11 +2,18 @@ package alibaba

 import (
 	"context"
+	"crypto/hmac"
+	"crypto/sha1"
+	"encoding/base64"
+	"math/rand"
+	"net/http"
+	"net/url"
 	"regexp"
+	"strconv"
+	"strings"
 	"time"

-	"github.com/aliyun/alibaba-cloud-sdk-go/services/ecs"
-	log "github.com/sirupsen/logrus"
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
 )
@@ -17,8 +24,11 @@ type Scanner struct{}
 var _ detectors.Detector = (*Scanner)(nil)

 var (
-	keyPat    = regexp.MustCompile(`\b(LTAI[a-zA-Z0-9]{17,21})[\"' ;\s]*`)
-	secretPat = regexp.MustCompile(`\b([a-zA-Z0-9]{30})\b`)
+	client = common.SaneHttpClient()
+
+	// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
+	keyPat = regexp.MustCompile(`\b([a-zA-Z0-9]{30})\b`)
+	idPat  = regexp.MustCompile(`\b(LTAI[a-zA-Z0-9]{17,21})[\"';\s]*`)
 )

 // Keywords are used for efficiently pre-filtering chunks.
@@ -27,58 +37,95 @@ func (s Scanner) Keywords() []string {
 	return []string{"LTAI"}
 }

+func randString(n int) string {
+	rand.Seed(time.Now().UnixNano())
+	const alphanum = "0123456789abcdefghijklmnopqrstuvwxyz"
+	var bytes = make([]byte, n)
+	rand.Read(bytes)
+	for i, b := range bytes {
+		bytes[i] = alphanum[b%byte(len(alphanum))]
+	}
+	return string(bytes)
+}
+
+func GetSignature(input, key string) string {
+	key_for_sign := []byte(key)
+	h := hmac.New(sha1.New, key_for_sign)
+	h.Write([]byte(input))
+	return base64.StdEncoding.EncodeToString(h.Sum(nil))
+}
+func buildStringToSign(method, input string) string {
+	filter := strings.Replace(input, "+", "%20", -1)
+	filter = strings.Replace(filter, "%7E", "~", -1)
+	filter = strings.Replace(filter, "*", "%2A", -1)
+	filter = method + "&%2F&" + url.QueryEscape(filter)
+	return filter
+}
+
 // FromData will find and optionally verify Alibaba 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)
 	matches := keyPat.FindAllStringSubmatch(dataStr, -1)
+	idMatches := idPat.FindAllStringSubmatch(dataStr, -1)
+
 	for _, match := range matches {
-		//Plausible key pat found, look for secrets match
-		secMatches := secretPat.FindAllStringSubmatch(dataStr, -1)
-
-		for _, secMatch := range secMatches {
-
 		if len(match) != 2 {
 			continue
 		}
+		resMatch := strings.TrimSpace(match[1])

-			s := detectors.Result{
+		for _, idMatch := range idMatches {
+			if len(idMatch) != 2 {
+				continue
+			}
+
+			resIdMatch := strings.TrimSpace(idMatch[1])
+
+			s1 := detectors.Result{
 				DetectorType: detectorspb.DetectorType_Alibaba,
-				Raw:          []byte(match[1]),
-				Redacted:     match[1],
+				Raw:          []byte(resMatch),
 			}

 			if verify {
-				ecsClient, err := ecs.NewClientWithAccessKey(
-					"us-east-1", // your region ID
-					match[1],    // your AccessKey ID
-					secMatch[1]) // your AccessKey Secret
+				req, err := http.NewRequestWithContext(ctx, "GET", "http://ecs.aliyuncs.com/?", nil)
 				if err != nil {
-					log.WithError(err).Debug("error creating alibaba client, skipping")
 					continue
 				}
-				// Create an API request and set parameters
-				request := ecs.CreateDescribeInstancesRequest()
-				request.ConnectTimeout = time.Duration(5) * time.Second
-				request.Scheme = "https"
-				request.Domain = "ecs.aliyuncs.com"
-				// Initiate the request and handle exceptions
-				_, err = ecsClient.DescribeInstances(request)
-				if err != nil {
-					s.Verified = false
+				dateISO := time.Now().UTC().Format("2006-01-02T15:04:05Z07:00")
+				params := req.URL.Query()
+				params.Add("AccessKeyId", resIdMatch)
+				params.Add("Action", "DescribeRegions")
+				params.Add("Format", "JSON")
+				params.Add("SignatureMethod", "HMAC-SHA1")
+				params.Add("SignatureNonce", randString(16))
+				params.Add("SignatureVersion", "1.0")
+				params.Add("Timestamp", dateISO)
+				params.Add("Version", "2014-05-26")

+				stringToSign := buildStringToSign(req.Method, params.Encode())
+				signature := GetSignature(stringToSign, resMatch+"&") //Get Signature HMAC SHA1
+				params.Add("Signature", signature)
+				req.URL.RawQuery = params.Encode()
+
+				req.Header.Add("Content-Type", "text/xml;charset=utf-8")
+				req.Header.Add("Content-Length", strconv.Itoa(len(params.Encode())))
+				res, err := client.Do(req)
+				if err == nil {
+					defer res.Body.Close()
+					if res.StatusCode >= 200 && res.StatusCode < 300 {
+						s1.Verified = true
 					} else {
-					s.Verified = true
-				}
-			}
-
-			if !s.Verified {
-				if detectors.IsKnownFalsePositive(string(s.Raw), detectors.DefaultFalsePositives, true) {
+						// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key.
+						if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
 							continue
 						}
 					}
+				}
+			}

-			results = append(results, s)
+			results = append(results, s1)
 		}
 	}
-	return
+
+	return detectors.CleanResults(results), nil
 }
@@ -7,20 +7,21 @@ import (
 	"time"

 	"github.com/kylelemons/godebug/pretty"
-	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
+
+	"github.com/trufflesecurity/trufflehog/v3/pkg/common"
 	"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
 )

 func TestAlibaba_FromChunk(t *testing.T) {
 	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
 	defer cancel()
-	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors2")
+	testSecrets, err := common.GetSecret(ctx, "trufflehog-testing", "detectors4")
 	if err != nil {
 		t.Fatalf("could not get test secrets from GCP: %s", err)
 	}
 	secret := testSecrets.MustGetField("ALIBABA_SECRET")
-	secretInactive := testSecrets.MustGetField("ALIBABA_SECRET_INACTIVE")
+	inactiveSecret := testSecrets.MustGetField("ALIBABA_SECRET_INACTIVE")
 	id := testSecrets.MustGetField("ALIBABA_ID")

 	type args struct {
@@ -40,14 +41,13 @@ func TestAlibaba_FromChunk(t *testing.T) {
 			s:    Scanner{},
 			args: args{
 				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("Alibaba keys are here: %s\n %s within", id, secret)),
+				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s", secret, id)),
 				verify: true,
 			},
 			want: []detectors.Result{
 				{
 					DetectorType: detectorspb.DetectorType_Alibaba,
 					Verified:     true,
-					Redacted:     id,
 				},
 			},
 			wantErr: false,
@@ -57,14 +57,13 @@ func TestAlibaba_FromChunk(t *testing.T) {
 			s:    Scanner{},
 			args: args{
 				ctx:    context.Background(),
-				data:   []byte(fmt.Sprintf("Alibaba keys are here: %s\n %s within", id, secretInactive)),
+				data:   []byte(fmt.Sprintf("You can find a alibaba secret %s within alibaba %s but not valid", inactiveSecret, id)), // the secret would satisfy the regex but not pass validation
 				verify: true,
 			},
 			want: []detectors.Result{
 				{
 					DetectorType: detectorspb.DetectorType_Alibaba,
 					Verified:     false,
-					Redacted:     id,
 				},
 			},
 			wantErr: false,
@@ -91,7 +90,7 @@ func TestAlibaba_FromChunk(t *testing.T) {
 			}
 			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])
 				}
 				got[i].Raw = nil
 			}
@@ -101,3 +100,18 @@ func TestAlibaba_FromChunk(t *testing.T) {
 		})
 	}
 }
+
+func BenchmarkFromData(benchmark *testing.B) {
+	ctx := context.Background()
+	s := Scanner{}
+	for name, data := range detectors.MustGetBenchmarkData() {
+		benchmark.Run(name, func(b *testing.B) {
+			for n := 0; n < b.N; n++ {
+				_, err := s.FromData(ctx, false, data)
+				if err != nil {
+					b.Fatal(err)
+				}
+			}
+		})
+	}
+}