agentic-actions-audito…
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI,…
Use when a bug PoC package needs an independent rerun and judgment before patching.
$ npx -y skills add trailofbits/skills --skill validate-bug --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/validate-bugContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when a bug PoC package needs an independent rerun and judgment before patching.
name: validate-bug description: Use when a bug PoC package needs an independent rerun and judgment before patching.
Use after `reproduce-bug` has supplied a finding and PoC package. Read the [record contract](../../references/records.md). Before target commands, follow its [project guidance](../../references/records.md#project-guidance).
Do not use to repair a PoC, develop a patch, or infer reproduction from the reproducer's narrative.
1. Read `finding.json`, the reproduction's proof type, commands, any PoC, and raw receipts. Do not read the reproducer's transcript. 2. Rerun the same baseline compiler command for compile failures, or rebuild and rerun the unchanged runtime PoC and planned scoped inputs. Save stdout, stderr, exit status and timing in `validate/receipts/`. If an observation is unreliable, return `inconclusive` instead of inferring either presence or absence. 3. Decide whether the target diagnostic or runtime assertion demonstrates the exact claim and violates the stated invariant. Write `validate.json` as `confirmed`, `not_confirmed`, or `inconclusive` with a short reason and agent identity.
[Validate record schema](../../schemas/validate.schema.json):
{
"schema_version": 1,
"outcome": "confirmed",
"agent": "validator-1",
"reason": "The unchanged PoC reached the assertion and demonstrated the claim."
}4. Manifest the complete `validate/` directory with `uv run --no-project <script> manifest <validate-step-dir>`, then run the [record checker](../../scripts/records.py). Return the package without editing the PoC or finding.
| Shortcut | Required action | | --- | --- | | Fix the PoC to make the claim work. | Mark it inconclusive and explain why. | | Trust the reproducer's conclusion. | Rerun the unchanged package independently. |
A Claude Code plugin marketplace from Trail of Bits providing skills to enhance AI-assisted security analysis, testing, and development workflows. Codex can load this marketplace through its Claude marketplace compatibility.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI,…
Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on…
Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing…
Prepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools,…
Scans Cairo/StarkNet smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messaging…
Systematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmetic safety, auditing…