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.

Jump to install

Repository: strmt7/ai_skills_collection_benchmarked
Last source activity: April 17, 2026 at 21:49
Detected SKILL.md language: English
Stars: 0
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/strmt7/ai_skills_collection_benchmarked --skill agentic-actions-auditor

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

agentic-actions-auditor

Use this skill when the task matches the description above or the source path clearly applies. Start with this concise entrypoint; open ../../../../../skills/by-category/security-compliance-risk/security-reference/agentic-actions-auditor/SKILL.md only when implementation details, commands, assets, or references are needed.

Workflow

Confirm the task matches this skill's scope.

Read the local source mirror if more detail is required.

Follow repository-level AGENTS.md; use one AI session only.

Keep claims tied to files, commands, citations, or benchmark artifacts.

Verification

Source mirror: ../../../../../skills/by-category/security-compliance-risk/security-reference/agentic-actions-auditor/SKILL.md

Source commit: e8cc5baf9329ccb491bfa200e82eacbac83b1ead

Static benchmark results: see docs/benchmark-results.md

Runtime artifacts recorded by this entrypoint: 0

Assigned scenarios: skill-proof-trailofbits-skills-plugins-agentic-actions-auditor-skills-agentic-actions-auditor-skill-md, security-compliance-and-risk-owasp-benchmark, security-compliance-and-risk-owasp-juice-shop, security-compliance-and-risk-kubernetes-examples

Do not claim this skill passed a runtime benchmark until a validated artifact exists.

name	agentic-actions-auditor
description	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.
source_skill_id	trailofbits-skills-plugins-agentic-actions-auditor-skills-agentic-actions-auditor-skill-md
category	Security, compliance & risk
source_mirror	../../../../../skills/by-category/security-compliance-risk/security-reference/agentic-actions-auditor/SKILL.md
benchmark_status	artifact_gated