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.
sharp-edges
sharp-edges is an open-source security skill for Claude Code and compatible agents, published by trailofbits. Its author describes it as: “Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether…”. 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 sharp-edges does
Evaluates whether APIs, configurations, and interfaces are resistant to developer misuse. Identifies designs where the "easy path" leads to insecurity.
Installation
Add sharp-edges 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 sharp-edges is organised into these sections:
- When to Use
- When NOT to Use
- Agent
- Core Principle
- Rationalizations to Reject
- Sharp Edge Categories
- 1. Algorithm/Mode Selection Footguns
- 2. Dangerous Defaults
- 3. Primitive vs. Semantic APIs
- 4. Configuration Cliffs
- 5. Silent Failures
- 6. Stringly-Typed Security
When to use it
Reach for sharp-edges 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 sharp-edges do?
- Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by default' and 'pit of success' principles. Triggers: footgun, misuse-resistant, secure defaults, API usability, dangerous configuration.
- How do I install sharp-edges?
- 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 sharp-edges free to use?
- Yes. sharp-edges 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 sharp-edges come from?
- sharp-edges 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.