This commit is contained in:
Zachary Rice 2023-07-10 09:07:50 -05:00
parent b38857edb4
commit 5557c91f79
4 changed files with 141 additions and 0 deletions

2
go.mod
View file

@ -82,6 +82,7 @@ require (
github.com/Microsoft/go-winio v0.6.1 // indirect
github.com/ProtonMail/go-crypto v0.0.0-20230518184743-7afd39499903 // indirect
github.com/acomagu/bufpipe v1.0.4 // indirect
github.com/alecthomas/chroma v0.10.0 // indirect
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751 // indirect
github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 // indirect
github.com/andybalholm/brotli v1.0.5 // indirect
@ -97,6 +98,7 @@ require (
github.com/couchbase/gocbcore/v10 v10.2.3 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/dimchansky/utfbom v1.1.1 // indirect
github.com/dlclark/regexp2 v1.4.0 // indirect
github.com/docker/cli v23.0.5+incompatible // indirect
github.com/docker/distribution v2.8.2+incompatible // indirect
github.com/docker/docker v23.0.5+incompatible // indirect

13
go.sum
View file

@ -64,6 +64,8 @@ github.com/TheZeroSlave/zapsentry v1.15.0 h1:w/YglG4Hc2L2VoEH6JKC+3YzhUL18/OZRjJ
github.com/TheZeroSlave/zapsentry v1.15.0/go.mod h1:D1YMfSuu6xnkhwFXxrronesmsiyDhIqo+86I3Ok+r64=
github.com/acomagu/bufpipe v1.0.4 h1:e3H4WUzM3npvo5uv95QuJM3cQspFNtFBzvJ2oNjKIDQ=
github.com/acomagu/bufpipe v1.0.4/go.mod h1:mxdxdup/WdsKVreO5GpW4+M/1CE2sMG4jeGJ2sYmHc4=
github.com/alecthomas/chroma v0.10.0 h1:7XDcGkCQopCNKjZHfYrNLraA+M7e0fMiJ/Mfikbfjek=
github.com/alecthomas/chroma v0.10.0/go.mod h1:jtJATyUxlIORhUOFNA9NZDWGAQ8wpxQQqNSB4rjA/1s=
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751 h1:JYp7IbQjafoB+tBA3gMyHYHrpOtNuDiK/uB5uXxq5wM=
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=
@ -135,6 +137,8 @@ github.com/denisenkom/go-mssqldb v0.12.3 h1:pBSGx9Tq67pBOTLmxNuirNTeB8Vjmf886Kx+
github.com/denisenkom/go-mssqldb v0.12.3/go.mod h1:k0mtMFOnU+AihqFxPMiF05rtiDrorD1Vrm1KEz5hxDo=
github.com/dimchansky/utfbom v1.1.1 h1:vV6w1AhK4VMnhBno/TPVCoK9U/LP0PkLCS9tbxHdi/U=
github.com/dimchansky/utfbom v1.1.1/go.mod h1:SxdoEBH5qIqFocHMyGOXVAybYJdr71b1Q/j0mACtrfE=
github.com/dlclark/regexp2 v1.4.0 h1:F1rxgk7p4uKjwIQxBs9oAXe5CqrXlCduYEJvrF4u93E=
github.com/dlclark/regexp2 v1.4.0/go.mod h1:2pZnwuY/m+8K6iRw6wQdMtk+rH5tNGR1i55kozfMjCc=
github.com/dnaeon/go-vcr v1.2.0/go.mod h1:R4UdLID7HZT3taECzJs4YgbbH6PIGXB6W/sc5OLb6RQ=
github.com/docker/cli v23.0.5+incompatible h1:ufWmAOuD3Vmr7JP2G5K3cyuNC4YZWiAsuDEvFVVDafE=
github.com/docker/cli v23.0.5+incompatible/go.mod h1:JLrzqnKDaYBop7H2jaqPtU4hHvMKP+vjCwu2uszcLI8=
@ -184,6 +188,7 @@ github.com/go-gl/glfw v0.0.0-20190409004039-e6da0acd62b1/go.mod h1:vR7hzQXu2zJy9
github.com/go-gl/glfw/v3.3/glfw v0.0.0-20191125211704-12ad95a8df72/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
github.com/go-ldap/ldap/v3 v3.4.5 h1:ekEKmaDrpvR2yf5Nc/DClsGG9lAmdDixe44mLzlW5r8=
github.com/go-ldap/ldap/v3 v3.4.5/go.mod h1:bMGIq3AGbytbaMwf8wdv5Phdxz0FWHTIYMSzyrYgnQs=
github.com/go-logfmt/logfmt v0.5.1/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs=
github.com/go-logr/logr v1.2.4 h1:g01GSCwiDw2xSZfjJ2/T9M+S6pFdcNtFYsp+Y43HYDQ=
github.com/go-logr/logr v1.2.4/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
github.com/go-logr/zapr v1.2.4 h1:QHVo+6stLbfJmYGkQ7uGHUCu5hnAFAj6mDe6Ea0SeOo=
@ -257,6 +262,7 @@ github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/go-containerregistry v0.14.0 h1:z58vMqHxuwvAsVwvKEkmVBz2TlgBgH5k6koEXBtlYkw=
github.com/google/go-containerregistry v0.14.0/go.mod h1:aiJ2fp/SXvkWgmYHioXnbMdlgB8eXiiYOY55gfN91Wk=
github.com/google/go-github/v39 v39.0.0/go.mod h1:C1s8C5aCC9L+JXIYpJM5GYytdX52vC1bLvHEF1IhBrE=
github.com/google/go-github/v42 v42.0.0 h1:YNT0FwjPrEysRkLIiKuEfSvBPCGKphW5aS5PxwaoLec=
github.com/google/go-github/v42 v42.0.0/go.mod h1:jgg/jvyI0YlDOM1/ps6XYh04HNQ3vKf0CVko62/EhRg=
github.com/google/go-github/v52 v52.0.0 h1:uyGWOY+jMQ8GVGSX8dkSwCzlehU3WfdxQ7GweO/JP7M=
@ -314,10 +320,13 @@ github.com/jmespath/go-jmespath/internal/testify v1.5.1 h1:shLQSRRSCCPj3f2gpwzGw
github.com/jmespath/go-jmespath/internal/testify v1.5.1/go.mod h1:L3OGu8Wl2/fWfCI6z80xFu9LTZmf1ZRjMHUOPmWr69U=
github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX5e0EB2j4=
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 v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
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=
github.com/julienschmidt/httprouter v1.3.0/go.mod h1:JR6WtHb+2LUe8TCKY3cZOxFyyO8IZAc4RVcycCCAKdM=
github.com/kevinburke/ssh_config v1.2.0 h1:x584FjTGwHzMwvHx18PXxbBVzfnxogHaAReU4gf13a4=
github.com/kevinburke/ssh_config v1.2.0/go.mod h1:CT57kijsi8u/K/BOFA39wgDQJ9CxiF4nAY/ojJ6r6mM=
github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
@ -354,9 +363,12 @@ github.com/mholt/archiver/v4 v4.0.0-alpha.8 h1:tRGQuDVPh66WCOelqe6LIGh0gwmfwxUrS
github.com/mholt/archiver/v4 v4.0.0-alpha.8/go.mod h1:5f7FUYGXdJWUjESffJaYR4R60VhnHxb2X3T1teMyv5A=
github.com/mitchellh/go-homedir v1.1.0 h1:lukF9ziXFxDFPkA1vsr5zpc1XuPDn/wFntq5mG+4E0Y=
github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
github.com/modocache/gover v0.0.0-20171022184752-b58185e213c5/go.mod h1:caMODM3PzxT8aQXRPkAt8xlV/e7d7w8GM5g0fa5F0D8=
github.com/montanaflynn/stats v0.0.0-20171201202039-1bf9dbcd8cbe h1:iruDEfMl2E6fbMZ9s0scYfZQ84/6SPL6zC8ACM2oIL0=
github.com/montanaflynn/stats v0.0.0-20171201202039-1bf9dbcd8cbe/go.mod h1:wL8QJuTMNUDYhXwkmfOly8iTdp5TEcJFWZD2D7SIkUc=
github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
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=
github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
@ -525,6 +537,7 @@ golang.org/x/lint v0.0.0-20190909230951-414d861bb4ac/go.mod h1:6SW0HCj/g11FgYtHl
golang.org/x/lint v0.0.0-20190930215403-16217165b5de/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
golang.org/x/lint v0.0.0-20191125180803-fdd1cda4f05f/go.mod h1:5qLYkcX4OjUUV8bRuDixDT3tpyyb+LUpUlRWLxfhWrs=
golang.org/x/lint v0.0.0-20200130185559-910be7a94367/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
golang.org/x/lint v0.0.0-20210508222113-6edffad5e616/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
golang.org/x/mobile v0.0.0-20190312151609-d3739f865fa6/go.mod h1:z+o9i4GpDbdi3rU15maQ/Ox0txvL9dWGYEHz965HBQE=
golang.org/x/mobile v0.0.0-20190719004257-d2bd2a29d028/go.mod h1:E/iHnbuqvinMTCcRqshq8CkpyQDoeVncDDYHnLhea+o=
golang.org/x/mod v0.0.0-20190513183733-4bf6d317e70e/go.mod h1:mXi4GBBbnImb6dmsKGUJ2LatrhH/nqhxcFungHvyanc=

View file

@ -2,6 +2,7 @@ package engine
import (
"bytes"
"fmt"
"reflect"
"runtime"
"strings"
@ -9,6 +10,8 @@ import (
"sync/atomic"
"time"
"github.com/alecthomas/chroma"
"github.com/alecthomas/chroma/lexers"
ahocorasick "github.com/petar-dambovaliev/aho-corasick"
"golang.org/x/sync/errgroup"
"google.golang.org/protobuf/proto"
@ -43,6 +46,9 @@ type Engine struct {
// prefilter is a ahocorasick struct used for doing efficient string
// matching given a set of words (keywords from the rules in the config)
prefilter ahocorasick.AhoCorasick
// v2 detection engine map, key is the length of characters in the secret capture group
v2Detectors map[int]detectors.Detector
}
type EngineOption func(*Engine)
@ -277,6 +283,20 @@ func (e *Engine) detectorWorker(ctx context.Context) {
continue
}
// use chroma to find all strings and comments
l := lexers.Analyse(string(chunk.Data))
if l != nil {
iterator, err := l.Tokenise(nil, string(chunk.Data))
if err != nil {
fmt.Println("error: ", err)
}
for _, token := range iterator.Tokens() {
if token.Type == chroma.LiteralString && len(token.Value) > 8 {
}
}
}
continue
// build a map of all keywords that were matched in the chunk
for _, m := range e.prefilter.FindAll(string(decoded.Data)) {
matchedKeywords[strings.ToLower(string(decoded.Data[m.Start():m.End()]))] = struct{}{}

View file

@ -0,0 +1,106 @@
package v2Detectors
import (
"context"
"regexp"
"unicode"
"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
"github.com/trufflesecurity/trufflehog/v3/pkg/pb/source_metadatapb"
"github.com/trufflesecurity/trufflehog/v3/pkg/pb/sourcespb"
"github.com/trufflesecurity/trufflehog/v3/pkg/sources"
)
// Detector defines an interface for scanning for and verifying secrets.
type DetectorV2 interface {
// FromData will scan bytes for results, and optionally verify them.
FromData(ctx context.Context, verify bool, data []byte) ([]Result, error)
Regexes() []*regexp.Regexp
}
type Result struct {
// DetectorType is the type of Detector.
DetectorType detectorspb.DetectorType
// DetectorName is the name of the Detector. Used for custom detectors.
DetectorName string
// DecoderType is the type of Decoder.
DecoderType detectorspb.DecoderType
Verified bool
// Raw contains the raw secret identifier data. Prefer IDs over secrets since it is used for deduping after hashing.
Raw []byte
// RawV2 contains the raw secret identifier that is a combination of both the ID and the secret.
// This is used for secrets that are multi part and could have the same ID. Ex: AWS credentials
RawV2 []byte
// Redacted contains the redacted version of the raw secret identification data for display purposes.
// A secret ID should be used if available.
Redacted string
ExtraData map[string]string
StructuredData *detectorspb.StructuredData
}
type ResultWithMetadata struct {
// SourceMetadata contains source-specific contextual information.
SourceMetadata *source_metadatapb.MetaData
// SourceID is the ID of the source that the API uses to map secrets to specific sources.
SourceID int64
// SourceType is the type of Source.
SourceType sourcespb.SourceType
// SourceName is the name of the Source.
SourceName string
Result
// Data from the sources.Chunk which this result was emitted for
Data []byte
}
// CopyMetadata returns a detector result with included metadata from the source chunk.
func CopyMetadata(chunk *sources.Chunk, result Result) ResultWithMetadata {
return ResultWithMetadata{
SourceMetadata: chunk.SourceMetadata,
SourceID: chunk.SourceID,
SourceType: chunk.SourceType,
SourceName: chunk.SourceName,
Result: result,
Data: chunk.Data,
}
}
// CleanResults returns all verified secrets, and if there are no verified secrets,
// just one unverified secret if there are any.
func CleanResults(results []Result) []Result {
if len(results) == 0 {
return results
}
var cleaned = make(map[string]Result, 0)
for _, s := range results {
if s.Verified {
cleaned[s.Redacted] = s
}
}
if len(cleaned) == 0 {
return results[:1]
}
results = results[:0]
for _, r := range cleaned {
results = append(results, r)
}
return results
}
// KeyIsRandom is a Low cost check to make sure that 'keys' include a number to reduce FPs.
// Golang doesn't support regex lookaheads, so must be done in separate calls.
// TODO improve checks. Shannon entropy did not work well.
func KeyIsRandom(key string) bool {
for _, ch := range key {
if unicode.IsDigit(ch) {
return true
}
}
return false
}