diff --git a/pkg/detectors/azurebatch/azurebatch.go b/pkg/detectors/azurebatch/azurebatch.go new file mode 100644 index 000000000000..576fcd43af40 --- /dev/null +++ b/pkg/detectors/azurebatch/azurebatch.go @@ -0,0 +1,114 @@ +package azurebatch + +import ( + "context" + "crypto/hmac" + "crypto/sha256" + "encoding/base64" + "fmt" + "net/http" + "regexp" + "strings" + "time" + + "github.com/trufflesecurity/trufflehog/v3/pkg/common" + "github.com/trufflesecurity/trufflehog/v3/pkg/detectors" + "github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb" +) + +type Scanner struct { + client *http.Client +} + +// Ensure the Scanner satisfies the interface at compile time. +var _ detectors.Detector = (*Scanner)(nil) + +var ( + defaultClient = common.SaneHttpClient() + // Make sure that your group is surrounded in boundary characters such as below to reduce false positives. + urlPat = regexp.MustCompile(`https://(.{1,50})\.(.{1,50})\.batch\.azure\.com`) + secretPat = regexp.MustCompile(`[A-Za-z0-9+/=]{88}`) +) + +// 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{".batch.azure.com"} +} + +// FromData will find and optionally verify Azurebatch 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) + + urlMatches := urlPat.FindAllStringSubmatch(dataStr, -1) + secretMatches := secretPat.FindAllStringSubmatch(dataStr, -1) + + for _, urlMatch := range urlMatches { + + for _, secretMatch := range secretMatches { + + endpoint := urlMatch[0] + accountName := urlMatch[1] + accountKey := secretMatch[0] + + s1 := detectors.Result{ + DetectorType: detectorspb.DetectorType_AzureBatch, + Raw: []byte(endpoint), + Redacted: endpoint, + RawV2: []byte(endpoint + accountKey), + } + + if verify { + client := s.client + if client == nil { + client = defaultClient + } + url := fmt.Sprintf("%s/applications?api-version=2020-09-01.12.0", endpoint) + date := time.Now().UTC().Format(http.TimeFormat) + stringToSign := fmt.Sprintf( + "GET\n\n\n\n\napplication/json\n%s\n\n\n\n\n\n%s\napi-version:%s", + date, + strings.ToLower(fmt.Sprintf("/%s/applications", accountName)), + "2020-09-01.12.0", + ) + key, _ := base64.StdEncoding.DecodeString(accountKey) + h := hmac.New(sha256.New, key) + h.Write([]byte(stringToSign)) + signature := base64.StdEncoding.EncodeToString(h.Sum(nil)) + req, err := http.NewRequest("GET", url, nil) + if err != nil { + continue + } + req.Header.Set("Content-Type", "application/json") + req.Header.Set("Authorization", fmt.Sprintf("SharedKey %s:%s", accountName, signature)) + req.Header.Set("Date", date) + resp, err := client.Do(req) + if err != nil { + continue + } + defer resp.Body.Close() + + if resp.StatusCode == http.StatusOK { + s1.Verified = 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 !s1.Verified && detectors.IsKnownFalsePositive(accountKey, detectors.DefaultFalsePositives, true) { + continue + } + + results = append(results, s1) + if s1.Verified { + break + } + } + } + + return results, nil +} + +func (s Scanner) Type() detectorspb.DetectorType { + return detectorspb.DetectorType_AzureBatch +} diff --git a/pkg/detectors/azurebatch/azurebatch_test.go b/pkg/detectors/azurebatch/azurebatch_test.go new file mode 100644 index 000000000000..b7a356275d66 --- /dev/null +++ b/pkg/detectors/azurebatch/azurebatch_test.go @@ -0,0 +1,130 @@ +//go:build detectors +// +build detectors + +package azurebatch + +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 TestAzurebatch_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) + } + url := testSecrets.MustGetField("AZUREBATCH_URL") + secret := testSecrets.MustGetField("AZUREBATCH_KEY") + inactiveSecret := testSecrets.MustGetField("AZUREBATCH_KEY_INACTIVE") + + type args struct { + ctx context.Context + data []byte + verify bool + } + tests := []struct { + name string + s Scanner + args args + want []detectors.Result + wantErr bool + wantVerificationErr bool + }{ + { + name: "found, verified", + s: Scanner{}, + args: args{ + ctx: context.Background(), + data: []byte(fmt.Sprintf("You can find a azurebatch secret %s and %s within", url, secret)), + verify: true, + }, + want: []detectors.Result{ + { + DetectorType: detectorspb.DetectorType_AzureBatch, + Verified: true, + }, + }, + wantErr: false, + wantVerificationErr: false, + }, + { + name: "found, unverified", + s: Scanner{}, + args: args{ + ctx: context.Background(), + data: []byte(fmt.Sprintf("You can find a azurebatch secret %s and %s within but not valid", url, inactiveSecret)), // the secret would satisfy the regex but not pass validation + verify: true, + }, + want: []detectors.Result{ + { + DetectorType: detectorspb.DetectorType_AzureBatch, + Verified: false, + }, + }, + wantErr: false, + wantVerificationErr: false, + }, + { + name: "not found", + s: Scanner{}, + args: args{ + ctx: context.Background(), + data: []byte("You cannot find the secret within"), + verify: true, + }, + want: nil, + wantErr: false, + wantVerificationErr: 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("AzureBatch.FromData() error = %v, wantErr %v", err, tt.wantErr) + return + } + for i := range got { + if len(got[i].Raw) == 0 { + 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) + } + } + ignoreOpts := cmpopts.IgnoreFields(detectors.Result{}, "RawV2", "Raw", "Redacted", "VerificationError") + + if diff := cmp.Diff(got, tt.want, ignoreOpts); diff != "" { + t.Errorf("AzureBatch.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) + } + } + }) + } +} diff --git a/pkg/engine/defaults.go b/pkg/engine/defaults.go index aad9f1ecebca..7ce1efca05a4 100644 --- a/pkg/engine/defaults.go +++ b/pkg/engine/defaults.go @@ -62,6 +62,7 @@ import ( "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/aylien" "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/ayrshare" "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/azure" + "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/azurebatch" "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/bannerbear" "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/baremetrics" "github.com/trufflesecurity/trufflehog/v3/pkg/detectors/beamer" @@ -780,6 +781,7 @@ func DefaultDetectors() []detectors.Detector { &alibaba.Scanner{}, aws.New(), &azure.Scanner{}, + &azurebatch.Scanner{}, &slack.Scanner{}, // has 4 secret types &gitlab.Scanner{}, &gitlabv2.Scanner{}, diff --git a/pkg/pb/detectorspb/detectors.pb.go b/pkg/pb/detectorspb/detectors.pb.go index df7d5b0243a1..73528bf93bee 100644 --- a/pkg/pb/detectorspb/detectors.pb.go +++ b/pkg/pb/detectorspb/detectors.pb.go @@ -1034,6 +1034,7 @@ const ( DetectorType_DenoDeploy DetectorType = 954 DetectorType_Stripo DetectorType = 955 DetectorType_ReplyIO DetectorType = 956 + DetectorType_AzureBatch DetectorType = 957 ) // Enum value maps for DetectorType. @@ -1992,6 +1993,7 @@ var ( 954: "DenoDeploy", 955: "Stripo", 956: "ReplyIO", + 957: "AzureBatch", } DetectorType_value = map[string]int32{ "Alibaba": 0, @@ -2947,6 +2949,7 @@ var ( "DenoDeploy": 954, "Stripo": 955, "ReplyIO": 956, + "AzureBatch": 957, } ) @@ -3325,7 +3328,7 @@ var file_detectors_proto_rawDesc = []byte{ 0x44, 0x65, 0x63, 0x6f, 0x64, 0x65, 0x72, 0x54, 0x79, 0x70, 0x65, 0x12, 0x0b, 0x0a, 0x07, 0x55, 0x4e, 0x4b, 0x4e, 0x4f, 0x57, 0x4e, 0x10, 0x00, 0x12, 0x09, 0x0a, 0x05, 0x50, 0x4c, 0x41, 0x49, 0x4e, 0x10, 0x01, 0x12, 0x0a, 0x0a, 0x06, 0x42, 0x41, 0x53, 0x45, 0x36, 0x34, 0x10, 0x02, 0x12, - 0x09, 0x0a, 0x05, 0x55, 0x54, 0x46, 0x31, 0x36, 0x10, 0x03, 0x2a, 0x8c, 0x78, 0x0a, 0x0c, 0x44, + 0x09, 0x0a, 0x05, 0x55, 0x54, 0x46, 0x31, 0x36, 0x10, 0x03, 0x2a, 0x9d, 0x78, 0x0a, 0x0c, 0x44, 0x65, 0x74, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x54, 0x79, 0x70, 0x65, 0x12, 0x0b, 0x0a, 0x07, 0x41, 0x6c, 0x69, 0x62, 0x61, 0x62, 0x61, 0x10, 0x00, 0x12, 0x08, 0x0a, 0x04, 0x41, 0x4d, 0x51, 0x50, 0x10, 0x01, 0x12, 0x07, 0x0a, 0x03, 0x41, 0x57, 0x53, 0x10, 0x02, 0x12, 0x09, 0x0a, 0x05, 0x41, @@ -4286,11 +4289,13 @@ var file_detectors_proto_rawDesc = []byte{ 0x0a, 0x08, 0x42, 0x75, 0x64, 0x69, 0x62, 0x61, 0x73, 0x65, 0x10, 0xb9, 0x07, 0x12, 0x0f, 0x0a, 0x0a, 0x44, 0x65, 0x6e, 0x6f, 0x44, 0x65, 0x70, 0x6c, 0x6f, 0x79, 0x10, 0xba, 0x07, 0x12, 0x0b, 0x0a, 0x06, 0x53, 0x74, 0x72, 0x69, 0x70, 0x6f, 0x10, 0xbb, 0x07, 0x12, 0x0c, 0x0a, 0x07, 0x52, - 0x65, 0x70, 0x6c, 0x79, 0x49, 0x4f, 0x10, 0xbc, 0x07, 0x42, 0x3d, 0x5a, 0x3b, 0x67, 0x69, 0x74, - 0x68, 0x75, 0x62, 0x2e, 0x63, 0x6f, 0x6d, 0x2f, 0x74, 0x72, 0x75, 0x66, 0x66, 0x6c, 0x65, 0x73, - 0x65, 0x63, 0x75, 0x72, 0x69, 0x74, 0x79, 0x2f, 0x74, 0x72, 0x75, 0x66, 0x66, 0x6c, 0x65, 0x68, - 0x6f, 0x67, 0x2f, 0x76, 0x33, 0x2f, 0x70, 0x6b, 0x67, 0x2f, 0x70, 0x62, 0x2f, 0x64, 0x65, 0x74, - 0x65, 0x63, 0x74, 0x6f, 0x72, 0x73, 0x70, 0x62, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33, + 0x65, 0x70, 0x6c, 0x79, 0x49, 0x4f, 0x10, 0xbc, 0x07, 0x12, 0x0f, 0x0a, 0x0a, 0x41, 0x7a, 0x75, + 0x72, 0x65, 0x42, 0x61, 0x74, 0x63, 0x68, 0x10, 0xbd, 0x07, 0x42, 0x3d, 0x5a, 0x3b, 0x67, 0x69, + 0x74, 0x68, 0x75, 0x62, 0x2e, 0x63, 0x6f, 0x6d, 0x2f, 0x74, 0x72, 0x75, 0x66, 0x66, 0x6c, 0x65, + 0x73, 0x65, 0x63, 0x75, 0x72, 0x69, 0x74, 0x79, 0x2f, 0x74, 0x72, 0x75, 0x66, 0x66, 0x6c, 0x65, + 0x68, 0x6f, 0x67, 0x2f, 0x76, 0x33, 0x2f, 0x70, 0x6b, 0x67, 0x2f, 0x70, 0x62, 0x2f, 0x64, 0x65, + 0x74, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x73, 0x70, 0x62, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, + 0x33, } var ( diff --git a/proto/detectors.proto b/proto/detectors.proto index 98d639cff2ea..0d4f75a58668 100644 --- a/proto/detectors.proto +++ b/proto/detectors.proto @@ -965,6 +965,7 @@ enum DetectorType { DenoDeploy = 954; Stripo = 955; ReplyIO = 956; + AzureBatch = 957; } message Result {