[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-trail-of-bits-trailmark-finding-triage":3,"mdc--n09mpu-key":38,"related-repo-trail-of-bits-trailmark-finding-triage":700,"related-org-trail-of-bits-trailmark-finding-triage":795},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":33,"sourceUrl":36,"mdContent":37},"trailmark-finding-triage","triage security findings using graph analysis","Performs graph-assisted triage of a single security finding, SARIF result, weAudit annotation, suspicious function, or report excerpt using Trailmark reachability, entrypoint paths, taint, privilege-boundary, blast-radius, caller\u002Fcallee, and neighborhood evidence. Use when deciding whether one candidate issue is reachable, prioritizing a finding before PoC work, preparing evidence for exploit validation, or checking whether a static-analysis result is actionable.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"trail-of-bits","Trail of Bits","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Ftrail-of-bits.png","trailofbits",[13,17,20,23],{"name":14,"slug":15,"type":16},"Security","security","tag",{"name":18,"slug":19,"type":16},"Graph Analysis","graph-analysis",{"name":21,"slug":22,"type":16},"Audit","audit",{"name":24,"slug":25,"type":16},"Code Analysis","code-analysis",6139,"https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills","2026-08-01T06:06:28.56006",null,541,[32],"agent-skills",{"repoUrl":27,"stars":26,"forks":30,"topics":34,"description":35},[32],"Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows","https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills\u002Ftree\u002FHEAD\u002Fplugins\u002Ftrailmark\u002Fskills\u002Ftrailmark-finding-triage","---\nname: trailmark-finding-triage\ndescription: \"Performs graph-assisted triage of a single security finding, SARIF result, weAudit annotation, suspicious function, or report excerpt using Trailmark reachability, entrypoint paths, taint, privilege-boundary, blast-radius, caller\u002Fcallee, and neighborhood evidence. Use when deciding whether one candidate issue is reachable, prioritizing a finding before PoC work, preparing evidence for exploit validation, or checking whether a static-analysis result is actionable.\"\nallowed-tools:\n  - Bash\n  - Read\n  - Grep\n  - Glob\n  - Write\n---\n\n# Trailmark Finding Triage\n\nBuild a concise graph evidence packet for one candidate finding. This skill\nanswers whether the affected code is reachable, what graph evidence supports\nor weakens the claim, and what manual review is still required before calling\nthe issue exploitable.\n\n## When to Use\n\n- Triage one static-analysis result before spending PoC time\n- Check whether a manual finding is entrypoint-reachable\n- Build an evidence packet for PoC work\n- Review a single suspicious function discovered during manual audit\n- Decide whether one issue should be promoted, deprioritized, or treated as\n  part of a broader chain analysis\n\n## When NOT to Use\n\n- Multiple weak findings might compose into a stronger chain. Use a chain or\n  composition workflow instead.\n- The user wants a full audit. Use an audit or design-review workflow instead.\n- The user wants remediation verification for a known finding. Use a\n  remediation-review workflow instead.\n- The target is a PR or branch diff. Use `graph-evolution` plus a differential\n  review workflow.\n- No concrete finding, function, file\u002Fline, or suspicious sink exists yet. Use\n  discovery skills first.\n\n## Rationalizations to Reject\n\n| Rationalization | Why It Is Wrong | Required Action |\n|---|---|---|\n| \"The scanner says high severity, so reachability is obvious\" | Static findings need graph and code context before promotion | Bind the finding to a graph node and check entrypoint paths |\n| \"No entrypoint path means impossible\" | It may mean parser, proxy, or dynamic dispatch limitations | Report the limitation separately from reachability |\n| \"An auth check appears on the path, so the issue is safe\" | The check may enforce the wrong predicate or be bypassed by another path | Treat validation\u002Fauth as review targets, not proof |\n| \"One reachable path is enough for a PoC claim\" | The path still needs attacker-controlled inputs and compatible preconditions | Separate graph reachability from exploitability |\n| \"This is probably a chain\" | Single-finding triage stops at one candidate | Hand off related findings to a composition workflow |\n\n## Workflow\n\n```\nFinding Triage Progress:\n- [ ] Step 1: Normalize the candidate\n- [ ] Step 2: Build or reuse the Trailmark graph\n- [ ] Step 3: Bind the candidate to graph node(s)\n- [ ] Step 4: Analyze reachability, taint, boundaries, and blast radius\n- [ ] Step 5: Decide and emit the evidence packet\n```\n\n### Step 1: Normalize the Candidate\n\nAccept file\u002Fline, function name, SARIF result, weAudit annotation, Markdown\nfinding excerpt, or a manual claim. Normalize it to:\n\n- title\n- source type\n- file path and line range if present\n- function or node hint\n- suspected source, sink, or asset\n- claimed impact\n\nIf there is no concrete code anchor, stop and ask for one.\n\nFor input handling details, see\n[references\u002Finput-normalization.md](references\u002Finput-normalization.md).\n\n### Step 2: Build Or Reuse The Graph\n\nUse the public `trailmark` skill workflow. Prefer an existing fresh exported\ngraph or `.trailmark\u002F` artifact when present. Otherwise build a graph with\n`language=\"auto\"` or the target's explicit language list, then run\n`engine.preanalysis()`.\n\nRecord the Trailmark version or feature probes used. Feature-gate Trailmark\n0.4-only APIs with `hasattr()` or CLI help checks.\n\n### Step 3: Bind The Candidate\n\nBind by file and line overlap first, then function name plus file. If several\nnodes match, list every candidate and select the narrowest enclosing node as\nprimary. If no node matches, report a binding limitation instead of guessing.\n\nSARIF and weAudit users should reuse the `audit-augmentation` workflow for\nmatching and then inspect the annotated node.\n\n### Step 4: Analyze Graph Evidence\n\nRun the query recipe in\n[references\u002Fquery-recipes.md](references\u002Fquery-recipes.md):\n\n- entrypoint paths to the bound node\n- trust level of each path when available\n- membership in `tainted`, `privilege_boundary`, and `high_blast_radius`\n  subgraphs\n- direct callers and callees\n- high-impact downstream sinks\n- sibling or nearby nodes worth manual review\n\nDo not treat graph reachability as proof of exploitability.\n\n### Step 5: Decide And Handoff\n\nProduce one verdict:\n\n| Verdict | Meaning |\n|---|---|\n| `Promote` | Graph evidence supports reachability and plausible impact |\n| `Needs manual review` | Evidence is suggestive but not decisive |\n| `Deprioritize` | No reachable path or only trusted\u002Finternal paths found |\n| `Blocked` | Binding or Trailmark analysis failed |\n\nWrite the evidence packet using\n[references\u002Foutput-format.md](references\u002Foutput-format.md).\n\nHand off promoted PoC-worthy issues to the user's PoC workflow. Hand off\nrelated findings to a composition workflow. Hand off repeatable root causes to\n`trailmark-variant-neighborhood`, `variant-analysis`, or a custom Semgrep\u002FCodeQL\nrule workflow.\n\n## Example Prompts\n\n- \"Use Trailmark finding triage on `src\u002FVault.sol:148`; I think withdraw can\n  bypass the balance update.\"\n- \"Triage this SARIF result before I spend PoC time: `semgrep:error\n  unchecked-transfer` in `contracts\u002FBridge.sol` line 91.\"\n- \"This report excerpt claims `parse_packet` is attacker reachable. Build the\n  Trailmark evidence packet and tell me what is still missing.\"\n",{"data":39,"body":46},{"name":4,"description":6,"allowed-tools":40},[41,42,43,44,45],"Bash","Read","Grep","Glob","Write",{"type":47,"children":48},"root",[49,57,63,70,100,106,143,149,272,278,290,297,302,335,340,353,359,395,408,414,419,432,438,450,507,512,518,523,613,624,644,650],{"type":50,"tag":51,"props":52,"children":53},"element","h1",{"id":4},[54],{"type":55,"value":56},"text","Trailmark Finding Triage",{"type":50,"tag":58,"props":59,"children":60},"p",{},[61],{"type":55,"value":62},"Build a concise graph evidence packet for one candidate finding. This skill\nanswers whether the affected code is reachable, what graph evidence supports\nor weakens the claim, and what manual review is still required before calling\nthe issue exploitable.",{"type":50,"tag":64,"props":65,"children":67},"h2",{"id":66},"when-to-use",[68],{"type":55,"value":69},"When to Use",{"type":50,"tag":71,"props":72,"children":73},"ul",{},[74,80,85,90,95],{"type":50,"tag":75,"props":76,"children":77},"li",{},[78],{"type":55,"value":79},"Triage one static-analysis result before spending PoC time",{"type":50,"tag":75,"props":81,"children":82},{},[83],{"type":55,"value":84},"Check whether a manual finding is entrypoint-reachable",{"type":50,"tag":75,"props":86,"children":87},{},[88],{"type":55,"value":89},"Build an evidence packet for PoC work",{"type":50,"tag":75,"props":91,"children":92},{},[93],{"type":55,"value":94},"Review a single suspicious function discovered during manual audit",{"type":50,"tag":75,"props":96,"children":97},{},[98],{"type":55,"value":99},"Decide whether one issue should be promoted, deprioritized, or treated as\npart of a broader chain analysis",{"type":50,"tag":64,"props":101,"children":103},{"id":102},"when-not-to-use",[104],{"type":55,"value":105},"When NOT to Use",{"type":50,"tag":71,"props":107,"children":108},{},[109,114,119,124,138],{"type":50,"tag":75,"props":110,"children":111},{},[112],{"type":55,"value":113},"Multiple weak findings might compose into a stronger chain. Use a chain or\ncomposition workflow instead.",{"type":50,"tag":75,"props":115,"children":116},{},[117],{"type":55,"value":118},"The user wants a full audit. Use an audit or design-review workflow instead.",{"type":50,"tag":75,"props":120,"children":121},{},[122],{"type":55,"value":123},"The user wants remediation verification for a known finding. Use a\nremediation-review workflow instead.",{"type":50,"tag":75,"props":125,"children":126},{},[127,129,136],{"type":55,"value":128},"The target is a PR or branch diff. Use ",{"type":50,"tag":130,"props":131,"children":133},"code",{"className":132},[],[134],{"type":55,"value":135},"graph-evolution",{"type":55,"value":137}," plus a differential\nreview workflow.",{"type":50,"tag":75,"props":139,"children":140},{},[141],{"type":55,"value":142},"No concrete finding, function, file\u002Fline, or suspicious sink exists yet. Use\ndiscovery skills first.",{"type":50,"tag":64,"props":144,"children":146},{"id":145},"rationalizations-to-reject",[147],{"type":55,"value":148},"Rationalizations to Reject",{"type":50,"tag":150,"props":151,"children":152},"table",{},[153,177],{"type":50,"tag":154,"props":155,"children":156},"thead",{},[157],{"type":50,"tag":158,"props":159,"children":160},"tr",{},[161,167,172],{"type":50,"tag":162,"props":163,"children":164},"th",{},[165],{"type":55,"value":166},"Rationalization",{"type":50,"tag":162,"props":168,"children":169},{},[170],{"type":55,"value":171},"Why It Is Wrong",{"type":50,"tag":162,"props":173,"children":174},{},[175],{"type":55,"value":176},"Required Action",{"type":50,"tag":178,"props":179,"children":180},"tbody",{},[181,200,218,236,254],{"type":50,"tag":158,"props":182,"children":183},{},[184,190,195],{"type":50,"tag":185,"props":186,"children":187},"td",{},[188],{"type":55,"value":189},"\"The scanner says high severity, so reachability is obvious\"",{"type":50,"tag":185,"props":191,"children":192},{},[193],{"type":55,"value":194},"Static findings need graph and code context before promotion",{"type":50,"tag":185,"props":196,"children":197},{},[198],{"type":55,"value":199},"Bind the finding to a graph node and check entrypoint paths",{"type":50,"tag":158,"props":201,"children":202},{},[203,208,213],{"type":50,"tag":185,"props":204,"children":205},{},[206],{"type":55,"value":207},"\"No entrypoint path means impossible\"",{"type":50,"tag":185,"props":209,"children":210},{},[211],{"type":55,"value":212},"It may mean parser, proxy, or dynamic dispatch limitations",{"type":50,"tag":185,"props":214,"children":215},{},[216],{"type":55,"value":217},"Report the limitation separately from reachability",{"type":50,"tag":158,"props":219,"children":220},{},[221,226,231],{"type":50,"tag":185,"props":222,"children":223},{},[224],{"type":55,"value":225},"\"An auth check appears on the path, so the issue is safe\"",{"type":50,"tag":185,"props":227,"children":228},{},[229],{"type":55,"value":230},"The check may enforce the wrong predicate or be bypassed by another path",{"type":50,"tag":185,"props":232,"children":233},{},[234],{"type":55,"value":235},"Treat validation\u002Fauth as review targets, not proof",{"type":50,"tag":158,"props":237,"children":238},{},[239,244,249],{"type":50,"tag":185,"props":240,"children":241},{},[242],{"type":55,"value":243},"\"One reachable path is enough for a PoC claim\"",{"type":50,"tag":185,"props":245,"children":246},{},[247],{"type":55,"value":248},"The path still needs attacker-controlled inputs and compatible preconditions",{"type":50,"tag":185,"props":250,"children":251},{},[252],{"type":55,"value":253},"Separate graph reachability from exploitability",{"type":50,"tag":158,"props":255,"children":256},{},[257,262,267],{"type":50,"tag":185,"props":258,"children":259},{},[260],{"type":55,"value":261},"\"This is probably a chain\"",{"type":50,"tag":185,"props":263,"children":264},{},[265],{"type":55,"value":266},"Single-finding triage stops at one candidate",{"type":50,"tag":185,"props":268,"children":269},{},[270],{"type":55,"value":271},"Hand off related findings to a composition workflow",{"type":50,"tag":64,"props":273,"children":275},{"id":274},"workflow",[276],{"type":55,"value":277},"Workflow",{"type":50,"tag":279,"props":280,"children":284},"pre",{"className":281,"code":283,"language":55},[282],"language-text","Finding Triage Progress:\n- [ ] Step 1: Normalize the candidate\n- [ ] Step 2: Build or reuse the Trailmark graph\n- [ ] Step 3: Bind the candidate to graph node(s)\n- [ ] Step 4: Analyze reachability, taint, boundaries, and blast radius\n- [ ] Step 5: Decide and emit the evidence packet\n",[285],{"type":50,"tag":130,"props":286,"children":288},{"__ignoreMap":287},"",[289],{"type":55,"value":283},{"type":50,"tag":291,"props":292,"children":294},"h3",{"id":293},"step-1-normalize-the-candidate",[295],{"type":55,"value":296},"Step 1: Normalize the Candidate",{"type":50,"tag":58,"props":298,"children":299},{},[300],{"type":55,"value":301},"Accept file\u002Fline, function name, SARIF result, weAudit annotation, Markdown\nfinding excerpt, or a manual claim. Normalize it to:",{"type":50,"tag":71,"props":303,"children":304},{},[305,310,315,320,325,330],{"type":50,"tag":75,"props":306,"children":307},{},[308],{"type":55,"value":309},"title",{"type":50,"tag":75,"props":311,"children":312},{},[313],{"type":55,"value":314},"source type",{"type":50,"tag":75,"props":316,"children":317},{},[318],{"type":55,"value":319},"file path and line range if present",{"type":50,"tag":75,"props":321,"children":322},{},[323],{"type":55,"value":324},"function or node hint",{"type":50,"tag":75,"props":326,"children":327},{},[328],{"type":55,"value":329},"suspected source, sink, or asset",{"type":50,"tag":75,"props":331,"children":332},{},[333],{"type":55,"value":334},"claimed impact",{"type":50,"tag":58,"props":336,"children":337},{},[338],{"type":55,"value":339},"If there is no concrete code anchor, stop and ask for one.",{"type":50,"tag":58,"props":341,"children":342},{},[343,345,351],{"type":55,"value":344},"For input handling details, see\n",{"type":50,"tag":346,"props":347,"children":349},"a",{"href":348},"references\u002Finput-normalization.md",[350],{"type":55,"value":348},{"type":55,"value":352},".",{"type":50,"tag":291,"props":354,"children":356},{"id":355},"step-2-build-or-reuse-the-graph",[357],{"type":55,"value":358},"Step 2: Build Or Reuse The Graph",{"type":50,"tag":58,"props":360,"children":361},{},[362,364,370,372,378,380,386,388,394],{"type":55,"value":363},"Use the public ",{"type":50,"tag":130,"props":365,"children":367},{"className":366},[],[368],{"type":55,"value":369},"trailmark",{"type":55,"value":371}," skill workflow. Prefer an existing fresh exported\ngraph or ",{"type":50,"tag":130,"props":373,"children":375},{"className":374},[],[376],{"type":55,"value":377},".trailmark\u002F",{"type":55,"value":379}," artifact when present. Otherwise build a graph with\n",{"type":50,"tag":130,"props":381,"children":383},{"className":382},[],[384],{"type":55,"value":385},"language=\"auto\"",{"type":55,"value":387}," or the target's explicit language list, then run\n",{"type":50,"tag":130,"props":389,"children":391},{"className":390},[],[392],{"type":55,"value":393},"engine.preanalysis()",{"type":55,"value":352},{"type":50,"tag":58,"props":396,"children":397},{},[398,400,406],{"type":55,"value":399},"Record the Trailmark version or feature probes used. Feature-gate Trailmark\n0.4-only APIs with ",{"type":50,"tag":130,"props":401,"children":403},{"className":402},[],[404],{"type":55,"value":405},"hasattr()",{"type":55,"value":407}," or CLI help checks.",{"type":50,"tag":291,"props":409,"children":411},{"id":410},"step-3-bind-the-candidate",[412],{"type":55,"value":413},"Step 3: Bind The Candidate",{"type":50,"tag":58,"props":415,"children":416},{},[417],{"type":55,"value":418},"Bind by file and line overlap first, then function name plus file. If several\nnodes match, list every candidate and select the narrowest enclosing node as\nprimary. If no node matches, report a binding limitation instead of guessing.",{"type":50,"tag":58,"props":420,"children":421},{},[422,424,430],{"type":55,"value":423},"SARIF and weAudit users should reuse the ",{"type":50,"tag":130,"props":425,"children":427},{"className":426},[],[428],{"type":55,"value":429},"audit-augmentation",{"type":55,"value":431}," workflow for\nmatching and then inspect the annotated node.",{"type":50,"tag":291,"props":433,"children":435},{"id":434},"step-4-analyze-graph-evidence",[436],{"type":55,"value":437},"Step 4: Analyze Graph Evidence",{"type":50,"tag":58,"props":439,"children":440},{},[441,443,448],{"type":55,"value":442},"Run the query recipe in\n",{"type":50,"tag":346,"props":444,"children":446},{"href":445},"references\u002Fquery-recipes.md",[447],{"type":55,"value":445},{"type":55,"value":449},":",{"type":50,"tag":71,"props":451,"children":452},{},[453,458,463,492,497,502],{"type":50,"tag":75,"props":454,"children":455},{},[456],{"type":55,"value":457},"entrypoint paths to the bound node",{"type":50,"tag":75,"props":459,"children":460},{},[461],{"type":55,"value":462},"trust level of each path when available",{"type":50,"tag":75,"props":464,"children":465},{},[466,468,474,476,482,484,490],{"type":55,"value":467},"membership in ",{"type":50,"tag":130,"props":469,"children":471},{"className":470},[],[472],{"type":55,"value":473},"tainted",{"type":55,"value":475},", ",{"type":50,"tag":130,"props":477,"children":479},{"className":478},[],[480],{"type":55,"value":481},"privilege_boundary",{"type":55,"value":483},", and ",{"type":50,"tag":130,"props":485,"children":487},{"className":486},[],[488],{"type":55,"value":489},"high_blast_radius",{"type":55,"value":491},"\nsubgraphs",{"type":50,"tag":75,"props":493,"children":494},{},[495],{"type":55,"value":496},"direct callers and callees",{"type":50,"tag":75,"props":498,"children":499},{},[500],{"type":55,"value":501},"high-impact downstream sinks",{"type":50,"tag":75,"props":503,"children":504},{},[505],{"type":55,"value":506},"sibling or nearby nodes worth manual review",{"type":50,"tag":58,"props":508,"children":509},{},[510],{"type":55,"value":511},"Do not treat graph reachability as proof of exploitability.",{"type":50,"tag":291,"props":513,"children":515},{"id":514},"step-5-decide-and-handoff",[516],{"type":55,"value":517},"Step 5: Decide And Handoff",{"type":50,"tag":58,"props":519,"children":520},{},[521],{"type":55,"value":522},"Produce one verdict:",{"type":50,"tag":150,"props":524,"children":525},{},[526,542],{"type":50,"tag":154,"props":527,"children":528},{},[529],{"type":50,"tag":158,"props":530,"children":531},{},[532,537],{"type":50,"tag":162,"props":533,"children":534},{},[535],{"type":55,"value":536},"Verdict",{"type":50,"tag":162,"props":538,"children":539},{},[540],{"type":55,"value":541},"Meaning",{"type":50,"tag":178,"props":543,"children":544},{},[545,562,579,596],{"type":50,"tag":158,"props":546,"children":547},{},[548,557],{"type":50,"tag":185,"props":549,"children":550},{},[551],{"type":50,"tag":130,"props":552,"children":554},{"className":553},[],[555],{"type":55,"value":556},"Promote",{"type":50,"tag":185,"props":558,"children":559},{},[560],{"type":55,"value":561},"Graph evidence supports reachability and plausible impact",{"type":50,"tag":158,"props":563,"children":564},{},[565,574],{"type":50,"tag":185,"props":566,"children":567},{},[568],{"type":50,"tag":130,"props":569,"children":571},{"className":570},[],[572],{"type":55,"value":573},"Needs manual review",{"type":50,"tag":185,"props":575,"children":576},{},[577],{"type":55,"value":578},"Evidence is suggestive but not decisive",{"type":50,"tag":158,"props":580,"children":581},{},[582,591],{"type":50,"tag":185,"props":583,"children":584},{},[585],{"type":50,"tag":130,"props":586,"children":588},{"className":587},[],[589],{"type":55,"value":590},"Deprioritize",{"type":50,"tag":185,"props":592,"children":593},{},[594],{"type":55,"value":595},"No reachable path or only trusted\u002Finternal paths found",{"type":50,"tag":158,"props":597,"children":598},{},[599,608],{"type":50,"tag":185,"props":600,"children":601},{},[602],{"type":50,"tag":130,"props":603,"children":605},{"className":604},[],[606],{"type":55,"value":607},"Blocked",{"type":50,"tag":185,"props":609,"children":610},{},[611],{"type":55,"value":612},"Binding or Trailmark analysis failed",{"type":50,"tag":58,"props":614,"children":615},{},[616,618,623],{"type":55,"value":617},"Write the evidence packet using\n",{"type":50,"tag":346,"props":619,"children":621},{"href":620},"references\u002Foutput-format.md",[622],{"type":55,"value":620},{"type":55,"value":352},{"type":50,"tag":58,"props":625,"children":626},{},[627,629,635,636,642],{"type":55,"value":628},"Hand off promoted PoC-worthy issues to the user's PoC workflow. Hand off\nrelated findings to a composition workflow. Hand off repeatable root causes to\n",{"type":50,"tag":130,"props":630,"children":632},{"className":631},[],[633],{"type":55,"value":634},"trailmark-variant-neighborhood",{"type":55,"value":475},{"type":50,"tag":130,"props":637,"children":639},{"className":638},[],[640],{"type":55,"value":641},"variant-analysis",{"type":55,"value":643},", or a custom Semgrep\u002FCodeQL\nrule workflow.",{"type":50,"tag":64,"props":645,"children":647},{"id":646},"example-prompts",[648],{"type":55,"value":649},"Example Prompts",{"type":50,"tag":71,"props":651,"children":652},{},[653,666,687],{"type":50,"tag":75,"props":654,"children":655},{},[656,658,664],{"type":55,"value":657},"\"Use Trailmark finding triage on ",{"type":50,"tag":130,"props":659,"children":661},{"className":660},[],[662],{"type":55,"value":663},"src\u002FVault.sol:148",{"type":55,"value":665},"; I think withdraw can\nbypass the balance update.\"",{"type":50,"tag":75,"props":667,"children":668},{},[669,671,677,679,685],{"type":55,"value":670},"\"Triage this SARIF result before I spend PoC time: ",{"type":50,"tag":130,"props":672,"children":674},{"className":673},[],[675],{"type":55,"value":676},"semgrep:error unchecked-transfer",{"type":55,"value":678}," in ",{"type":50,"tag":130,"props":680,"children":682},{"className":681},[],[683],{"type":55,"value":684},"contracts\u002FBridge.sol",{"type":55,"value":686}," line 91.\"",{"type":50,"tag":75,"props":688,"children":689},{},[690,692,698],{"type":55,"value":691},"\"This report excerpt claims ",{"type":50,"tag":130,"props":693,"children":695},{"className":694},[],[696],{"type":55,"value":697},"parse_packet",{"type":55,"value":699}," is attacker reachable. Build the\nTrailmark evidence packet and tell me what is still missing.\"",{"items":701,"total":794},[702,719,729,747,760,773,785],{"slug":703,"name":703,"fn":704,"description":705,"org":706,"tags":707,"stars":26,"repoUrl":27,"updatedAt":718},"address-sanitizer","detect memory errors during fuzzing","AddressSanitizer detects memory errors during fuzzing. Use when fuzzing C\u002FC++ code to find buffer overflows and use-after-free bugs.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[708,711,714,715],{"name":709,"slug":710,"type":16},"C#","c",{"name":712,"slug":713,"type":16},"Debugging","debugging",{"name":14,"slug":15,"type":16},{"name":716,"slug":717,"type":16},"Testing","testing","2026-07-17T06:05:14.925095",{"slug":720,"name":720,"fn":721,"description":722,"org":723,"tags":724,"stars":26,"repoUrl":27,"updatedAt":728},"aflpp","perform multi-core fuzzing of C\u002FC++ projects","AFL++ is a fork of AFL with better fuzzing performance and advanced features. Use for multi-core fuzzing of C\u002FC++ projects.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[725,726,727],{"name":709,"slug":710,"type":16},{"name":14,"slug":15,"type":16},{"name":716,"slug":717,"type":16},"2026-07-17T06:05:12.433192",{"slug":730,"name":730,"fn":731,"description":732,"org":733,"tags":734,"stars":26,"repoUrl":27,"updatedAt":746},"agentic-actions-auditor","audit GitHub Actions for security vulnerabilities","Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI\u002FCD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI\u002FCD pipeline security for prompt injection risks, or evaluating agentic action configurations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[735,738,741,742,745],{"name":736,"slug":737,"type":16},"Agents","agents",{"name":739,"slug":740,"type":16},"CI\u002FCD","ci-cd",{"name":24,"slug":25,"type":16},{"name":743,"slug":744,"type":16},"GitHub Actions","github-actions",{"name":14,"slug":15,"type":16},"2026-07-18T05:47:48.564744",{"slug":748,"name":748,"fn":749,"description":750,"org":751,"tags":752,"stars":26,"repoUrl":27,"updatedAt":759},"algorand-vulnerability-scanner","scan Algorand smart contracts for vulnerabilities","Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues. Use when auditing Algorand projects (TEAL\u002FPyTeal).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[753,754,755,756],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":757,"slug":758,"type":16},"Smart Contracts","smart-contracts","2026-07-18T05:47:43.989063",{"slug":761,"name":761,"fn":762,"description":763,"org":764,"tags":765,"stars":26,"repoUrl":27,"updatedAt":772},"ask-questions-if-underspecified","clarify requirements before implementation","Clarify requirements before implementing. Use when serious doubts arise.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[766,769],{"name":767,"slug":768,"type":16},"Engineering","engineering",{"name":770,"slug":771,"type":16},"Productivity","productivity","2026-07-17T06:05:33.543262",{"slug":774,"name":774,"fn":775,"description":776,"org":777,"tags":778,"stars":26,"repoUrl":27,"updatedAt":784},"atheris","fuzz Python code with Atheris","Atheris is a coverage-guided Python fuzzer based on libFuzzer. Use for fuzzing pure Python code and Python C extensions.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[779,782,783],{"name":780,"slug":781,"type":16},"Python","python",{"name":14,"slug":15,"type":16},{"name":716,"slug":717,"type":16},"2026-07-17T06:05:14.575191",{"slug":429,"name":429,"fn":786,"description":787,"org":788,"tags":789,"stars":26,"repoUrl":27,"updatedAt":793},"augment code graphs with audit findings","Augments Trailmark code graphs with external audit findings from SARIF static analysis results, weAudit annotation files, and version-gated Trailmark 0.4.x binary-analysis graph exports. Maps findings to graph nodes by file and line overlap, creates severity-based subgraphs, and enables cross-referencing findings with pre-analysis data (blast radius, taint, etc.). Use when projecting SARIF results onto a code graph, overlaying weAudit annotations, importing binary graph findings, cross-referencing Semgrep, CodeQL, or binary-analysis findings with call graph data, or visualizing audit findings in the context of code structure.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[790,791,792],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},"2026-08-01T05:44:54.920542",77,{"items":796,"total":900},[797,804,810,818,825,830,836,842,855,866,878,889],{"slug":703,"name":703,"fn":704,"description":705,"org":798,"tags":799,"stars":26,"repoUrl":27,"updatedAt":718},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[800,801,802,803],{"name":709,"slug":710,"type":16},{"name":712,"slug":713,"type":16},{"name":14,"slug":15,"type":16},{"name":716,"slug":717,"type":16},{"slug":720,"name":720,"fn":721,"description":722,"org":805,"tags":806,"stars":26,"repoUrl":27,"updatedAt":728},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[807,808,809],{"name":709,"slug":710,"type":16},{"name":14,"slug":15,"type":16},{"name":716,"slug":717,"type":16},{"slug":730,"name":730,"fn":731,"description":732,"org":811,"tags":812,"stars":26,"repoUrl":27,"updatedAt":746},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[813,814,815,816,817],{"name":736,"slug":737,"type":16},{"name":739,"slug":740,"type":16},{"name":24,"slug":25,"type":16},{"name":743,"slug":744,"type":16},{"name":14,"slug":15,"type":16},{"slug":748,"name":748,"fn":749,"description":750,"org":819,"tags":820,"stars":26,"repoUrl":27,"updatedAt":759},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[821,822,823,824],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":757,"slug":758,"type":16},{"slug":761,"name":761,"fn":762,"description":763,"org":826,"tags":827,"stars":26,"repoUrl":27,"updatedAt":772},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[828,829],{"name":767,"slug":768,"type":16},{"name":770,"slug":771,"type":16},{"slug":774,"name":774,"fn":775,"description":776,"org":831,"tags":832,"stars":26,"repoUrl":27,"updatedAt":784},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[833,834,835],{"name":780,"slug":781,"type":16},{"name":14,"slug":15,"type":16},{"name":716,"slug":717,"type":16},{"slug":429,"name":429,"fn":786,"description":787,"org":837,"tags":838,"stars":26,"repoUrl":27,"updatedAt":793},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[839,840,841],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"slug":843,"name":843,"fn":844,"description":845,"org":846,"tags":847,"stars":26,"repoUrl":27,"updatedAt":854},"audit-context-building","build architectural context for code analysis","Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[848,851,852,853],{"name":849,"slug":850,"type":16},"Architecture","architecture",{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":767,"slug":768,"type":16},"2026-07-18T05:47:40.122449",{"slug":856,"name":856,"fn":857,"description":858,"org":859,"tags":860,"stars":26,"repoUrl":27,"updatedAt":865},"audit-prep-assistant","prepare codebases for security audits","Prepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates documentation (flowcharts, user stories, inline comments).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[861,862,863,864],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":767,"slug":768,"type":16},{"name":14,"slug":15,"type":16},"2026-07-18T05:47:39.210985",{"slug":867,"name":867,"fn":868,"description":869,"org":870,"tags":871,"stars":26,"repoUrl":27,"updatedAt":877},"burpsuite-project-parser","parse Burp Suite project files","Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns, extracting security audit findings, dumping proxy history or site map data, or analyzing HTTP traffic captured in a Burp project.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[872,873,876],{"name":21,"slug":22,"type":16},{"name":874,"slug":875,"type":16},"CLI","cli",{"name":14,"slug":15,"type":16},"2026-07-17T06:05:33.198077",{"slug":879,"name":879,"fn":880,"description":881,"org":882,"tags":883,"stars":26,"repoUrl":27,"updatedAt":888},"c-review","audit C and C++ code","Performs comprehensive C\u002FC++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities. Use when auditing native C\u002FC++ applications, reviewing daemons or services for memory safety, or hunting integer overflow \u002F use-after-free \u002F race conditions in userspace code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[884,885,886,887],{"name":21,"slug":22,"type":16},{"name":709,"slug":710,"type":16},{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},"2026-07-17T06:05:11.333374",{"slug":890,"name":890,"fn":891,"description":892,"org":893,"tags":894,"stars":26,"repoUrl":27,"updatedAt":899},"cairo-vulnerability-scanner","scan Cairo and StarkNet contracts for vulnerabilities","Scans Cairo\u002FStarkNet smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messaging issues, address conversion problems, and signature replay. Use when auditing StarkNet projects.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[895,896,897,898],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":757,"slug":758,"type":16},"2026-07-18T05:47:42.84568",111]