Compare commits

...

1 Commits

Author SHA1 Message Date
Zachary Rice fa3e9f8822 add levenshtein distance check 2023-07-11 12:00:52 -05:00
3 changed files with 24 additions and 5 deletions
+1
View File
@@ -127,6 +127,7 @@ 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/ka-weihe/fast-levenshtein v0.0.0-20201227151214-4c99ee36a1ba // indirect
github.com/kevinburke/ssh_config v1.2.0 // indirect
github.com/klauspost/compress v1.16.5 // indirect
github.com/klauspost/pgzip v1.2.5 // indirect
+15
View File
@@ -64,6 +64,7 @@ github.com/TheZeroSlave/zapsentry v1.17.0 h1:RIQCG89U7vWWZVmmCxeUz/g32WEcAYXUrXH
github.com/TheZeroSlave/zapsentry v1.17.0/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/agnivade/levenshtein v1.1.0/go.mod h1:veldBMzWxcCG2ZvUTKD2kJNRdCk5hVbJomOvKkmgYbo=
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=
@@ -74,6 +75,7 @@ github.com/andybalholm/brotli v1.0.5 h1:8uQZIdzKmjc/iuPu7O2ioW48L81FgatrcpfFmiq/
github.com/andybalholm/brotli v1.0.5/go.mod h1:fO7iG3H7G2nSZ7m0zPUDn85XEX2GTukHGRSepvi9Eig=
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be h1:9AeTilPcZAjCFIImctFaOjnTIavg87rW78vTPkQqLI8=
github.com/antihax/optional v1.0.0/go.mod h1:uupD/76wgC+ih3iEmQUL+0Ugr19nfwCT1kdvxnR2qWY=
github.com/arbovm/levenshtein v0.0.0-20160628152529-48b4e1c0c4d0/go.mod h1:t2tdKJDJF9BV14lnkjHmOQgcvEKgtqs5a1N3LNdJhGE=
github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5 h1:0CwZNZbxp69SHPdPJAN/hZIm0C4OItdklCFmMRWYpio=
github.com/aws/aws-sdk-go v1.44.83 h1:7+Rtc2Eio6EKUNoZeMV/IVxzVrY5oBQcNPtCcgIHYJA=
github.com/aws/aws-sdk-go v1.44.83/go.mod h1:y4AeaBuwd2Lk+GepC1E9v0qOiTws0MIWAX4oIKwKHZo=
@@ -133,6 +135,8 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/denisenkom/go-mssqldb v0.12.3 h1:pBSGx9Tq67pBOTLmxNuirNTeB8Vjmf886Kx+8Y+8shw=
github.com/denisenkom/go-mssqldb v0.12.3/go.mod h1:k0mtMFOnU+AihqFxPMiF05rtiDrorD1Vrm1KEz5hxDo=
github.com/dgryski/trifles v0.0.0-20200323201526-dd97f9abfb48/go.mod h1:if7Fbed8SFyPtHLHbg49SI7NAdJiC5WIA09pe59rfAA=
github.com/dgryski/trifles v0.0.0-20200830180326-aaf60a07f6a3/go.mod h1:if7Fbed8SFyPtHLHbg49SI7NAdJiC5WIA09pe59rfAA=
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/dnaeon/go-vcr v1.2.0/go.mod h1:R4UdLID7HZT3taECzJs4YgbbH6PIGXB6W/sc5OLb6RQ=
@@ -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 +320,15 @@ 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/ka-weihe/fast-levenshtein v0.0.0-20201227151214-4c99ee36a1ba h1:keZ4vJpYOVm6yrjLzZ6QgozbEBaT0GjfH30ihbO67+4=
github.com/ka-weihe/fast-levenshtein v0.0.0-20201227151214-4c99ee36a1ba/go.mod h1:kaXTPU4xitQT0rfT7/i9O9Gm8acSh3DXr0p4y3vKqiE=
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 +365,12 @@ 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 +539,7 @@ 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=
+8 -5
View File
@@ -9,6 +9,8 @@ import (
"sync/atomic"
"time"
levenshtein "github.com/ka-weihe/fast-levenshtein"
ahocorasick "github.com/petar-dambovaliev/aho-corasick"
"golang.org/x/sync/errgroup"
"google.golang.org/protobuf/proto"
@@ -276,15 +278,16 @@ func (e *Engine) detectorWorker(ctx context.Context) {
original := chunk.Data
decoded := decoder.FromChunk(chunk)
if decoded == nil {
continue
}
if decoded == nil ||
// check if the decoded data is similar "enough" to the original data. If it is, then we can skip scanning the decoded data as
// it's likely already picked up by the PLAIN decoder. See related issue: https://github.com/trufflesecurity/trufflehog/issues/1450
(decoded != nil &&
decoderType == detectorspb.DecoderType_BASE64 && common.BytesEqual(original, decoded.Data, 40)) {
// quick performant test to see if the decoded data is similar enough to the original data
decoderType == detectorspb.DecoderType_BASE64 && common.BytesEqual(original, decoded.Data, 40) &&
// more accurate test to see if the decoded data is similar enough to the original data.
// Explainer: if the levenshtein distance is less than half the length of the original string, then it's likely similar enough
// to the original string to be picked up by the PLAIN decoder. This is a very rough heuristic, but it's better than nothing.
levenshtein.Distance(string(original), string(decoded.Data)) < (len(original)/2)) {
continue
}