trailofbits-review
Skill2 starsChanged 21 days agoMITView on GitHub
Manual pointer to pinned Trail of Bits rust-review and differential-review. Use for genos-engine (Rust, unsafe GPU/FFI) or a security-sensitive PR diff.
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- act-within-scopeSkill
- build-filesSkill
- codingSkill
- context-managementSkill
- create-verification-skillSkill
- docxSkill
- domain-modelingSkill
- encode-lessonsSkill
- experience-firstSkill
- eyes-onSkill
- fluxSkill
- frontend-designSkill
- gitSkill
- grill-with-docsSkill
- handoffSkill
- in-your-own-wordsSkill
- lint-rulesSkill
- maintain-verification-skillSkill
- pdfSkill
- renderdoc-gpu-debugSkill
- scripted-verificationSkill
- security-auditSkill
- skill-evaluationSkill
- test-auditSkill
- test-behavior-not-implementationSkill
- writingSkill
- xlsxSkill
The file
Files
Trail of Bits review
This skill is a router. It does not contain the Trail of Bits audit. Those
plugins are CC-BY-SA-4.0 and stay in trailofbits/skills. Do not paste their
prompts, skill text, or agent instructions into this repository.
When to use it
rust-review: Rust security review, including genos-engine code that usesunsafe, GPU code, or FFI.differential-review: a security-sensitive pull request diff.
Invoke this skill by name. Do not load it for ordinary edits. Each audit is large and spends a lot of tokens.
Steps
The pin below is copied from third-party/pins.json in the agent-skills
repository. Use this copy. A consumer checkout, plugin install, or
npx skills add does not include that file.
Pinned commit: e4dd0bb5b15535f7c5a0834187dffba6ac37e4ff
Install both plugins at that commit. This writes them on the machine that runs the command. It does not add them to the MIT agent-skills tree.
npx skills add trailofbits/skills@e4dd0bb5b15535f7c5a0834187dffba6ac37e4ff --skill rust-review --skill differential-review --full-depthThen run the installed upstream plugin. Do not follow main. Attribute the
result to Trail of Bits under CC-BY-SA-4.0.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

