🛡️
AI EngineeringPython

Agentic Actions Auditor

by trailofbits

Agentic Actions Auditor is an AI Engineering skill for Claude Code, published by trailofbits in skills.

6.6K stars567 forkson trailofbits/skillsAdded 2026/08/15Repository updated 2026/08/14
View source on GitHubDownload repo ZIP
agent-skills
Install in seconds
Install Agentic Actions Auditor
Copy Agentic Actions Auditor into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/trailofbits/skills/tree/main/plugins/agentic-actions-auditor/skills/agentic-actions-auditor ~/.claude/skills/agentic-actions-auditor

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/trailofbits/skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
plugins/agentic-actions-auditor/skills/agentic-actions-auditor/SKILL.md in trailofbits/skills
Installs to
~/.claude/skills/agentic-actions-auditor
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering — 2451 skills

What Agentic Actions Auditor does

Agentic Actions Auditor provides static security analysis guidance for GitHub Actions workflows that invoke AI coding agents, detecting attack vectors where attacker-controlled input reaches an AI agent. Use it when auditing CI/CD pipeline security for prompt injection risks or evaluating agentic action configurations.

Agentic Actions Auditor is cataloged under AI Engineering on DirSkills. Agentic Actions Auditor comes from a repository tagged agent-skills.

Documentation

README

Agentic Actions Auditor

Static security analysis guidance for GitHub Actions workflows that invoke AI coding agents. This skill teaches you how to discover workflow files locally or from remote GitHub repositories, identify AI action steps, follow cross-file references to composite actions and reusable workflows that may contain hidden AI agents, capture security-relevant configuration, and detect attack vectors where attacker-controlled input reaches an AI agent running in a CI/CD pipeline.

When to Use

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Agentic Actions Auditor

  • What else does trailofbits publish alongside Agentic Actions Auditor?

    Agentic Actions Auditor is one of 25 skills that DirSkills catalogs from trailofbits/skills, the repository it ships in. Its siblings there include Algorand Vulnerability Scanner, Audit Context Building and Audit Prep Assistant. Each one is a separate skill with its own page in this directory, installs the same way Agentic Actions Auditor does, and is maintained by trailofbits in that same repository. The rest of the collection is listed on the trailofbits/skills page.

  • How does Agentic Actions Auditor compare to other AI Engineering skills?

    Agentic Actions Auditor ranks #431 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agentic Actions Auditor against them. Open each page to compare what they document and how they install.

More from trailofbits/skills

Agentic Actions Auditor is one of 25 skills cataloged on DirSkills from trailofbits/skills.

See all 25 skills →
🔍
2w ago

Algorand Vulnerability Scanner

Algorand Vulnerability Scanner scans TEAL and PyTeal smart contracts for 11 common Algorand vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues. Use it when auditing Algorand projects or training on Algorand-specific security patterns.
Quality
6.6K567
🗺️
2w ago

Audit Context Building

Audit Context Building analyzes an unfamiliar codebase to map functions, assumptions, guarantees, and dependencies before any vulnerability hunting. Use it at the start of an audit, threat model, or architecture review to produce dossiers and open questions that feed later phases.
Quality
6.6K567
🛡️
2w ago

Audit Prep Assistant

Audit Prep Assistant prepares codebases for security reviews using Trail of Bits' checklist. It helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates documentation.
Quality
6.6K567
🔎
2w ago

Burp Suite Project Parser

Burp Suite Project Parser searches and explores Burp Suite project files (.burp) from the command line. Use it when searching response headers or bodies with regex patterns, extracting security audit findings, dumping proxy history or site map data, or analyzing HTTP traffic captured in a Burp project.
Quality
6.6K567
🛡️
2w ago

C/C++ Security Review

C/C++ Security Review performs comprehensive security audits of native C/C++ applications for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities. Use it when auditing userspace daemons, services, or applications for memory safety issues.
Quality
6.6K567
🛡️
2w ago

Cairo StarkNet Vulnerability Scanner

Cairo StarkNet Vulnerability Scanner scans Cairo smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messaging issues, address conversion problems, and signature replay. Use it when auditing StarkNet projects.
Quality
6.6K567

More AI Engineering skills

Agentic Actions Auditor is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #431 by stars among them.

Browse all AI Engineering skills →
📐
3w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
3w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
3w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K