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/CD 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/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
fp-check
fp-check is an open-source security skill for Claude Code and compatible agents, published by trailofbits. Its author describes it as: “Systematically verifies suspected security bugs to eliminate false positives, producing a TRUE POSITIVE or FALSE POSITIVE verdict with documented evidence for each. Use when asked whether a specific finding is real, e…”. The project has 6.6k stars on GitHub and is available under the CC-BY-SA-4.0 license. Add it to your setup with `/plugin marketplace add trailofbits/skills`.
What fp-check does
- "Is this bug real?" or "is this a true positive?" - "Is this a false positive?" or "verify this finding" - "Check if this vulnerability is exploitable" - Any request to verify or validate a specific suspected bug
Installation
Add fp-check to your agent with:
/plugin marketplace add trailofbits/skillsAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for fp-check is organised into these sections:
- When to Use
- When NOT to Use
- Rationalizations to Reject
- Step 0: Understand the Claim and Context
- Route: Standard vs Deep Verification
- Standard Verification
- Deep Verification
- Default
- Batch Triage
- Final Summary
- References
When to use it
Reach for fp-check when you want security help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear CC-BY-SA-4.0 license — safe to read and adapt
- Ships in trailofbits/skills, an established project with 6,646 GitHub stars
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does fp-check do?
- Systematically verifies suspected security bugs to eliminate false positives, producing a TRUE POSITIVE or FALSE POSITIVE verdict with documented evidence for each. Use when asked whether a specific finding is real, exploitable, or a false positive, or to verify or validate a suspected vulnerability — not for hunting or discovering new bugs.
- How do I install fp-check?
- Run /plugin marketplace add trailofbits/skills in your agent, then reload your skills. Review the source at https://github.com/trailofbits/skills before installing.
- Is fp-check free to use?
- Yes. fp-check is free and open source under the CC-BY-SA-4.0 license, so you can read, run, and adapt it within that license's terms.
- Where does fp-check come from?
- fp-check ships inside trailofbits/skills, a repository that contains 41 catalogued skills in total. The repository's 6,646 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Security →Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review on unfamiliar code, and before any vulnerability-hunting pass.
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/PyTeal).
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).
Scans Cairo/StarkNet 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.