agentic-actions-auditor
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 …
What is this resource?
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 …
Review the original project for installation steps, licenses, compatibility and updates. This directory provides discovery links, not downloadable or verified code.
Installation
For repositories supported by the Skills CLI, you can typically start with:
npx skills add trailofbits/skillsCheck the repository instructions and select the intended skill before installing. This command may not apply to every source.
Safety & attribution
This is an external resource, not independently security-audited by this directory. Inspect permissions, scripts and changes before using it with your files or accounts.