agentic-actions-auditor SKILL.md skillA
agentic-actions-auditor from trailofbits/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add trailofbits/skills/agentic-actions-auditor@git:20260831.9645e2fPins git:20260831.9645e2f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- trailofbits/skills
- Path
plugins/agentic-actions-auditor/skills/agentic-actions-auditor/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260831.9645e2f, committed Aug 31, 2026
- First version recorded
- Feb 26, 2026
- Size
- 21,743 bytes
- Repository stars
- 7,698
- License
- CC-BY-SA-4.0
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…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 - Auditing a repository's GitHub Actions workflows for AI agent security - Reviewing CI/CD configurations that invoke Claude Code Action, Gemini CLI, or OpenAI Codex - Checking whether attacker-controlled input can reach AI agent prompts - Evaluating agentic action configurations (sandbox settings, tool permissions, user allowlists) - Assessing trigger events that expose workflows to external input (`pull_request_target`, `issue_comment`, etc.) - Investigating data flow from GitHub event context through `env:` blocks to AI prompt fields ## When NOT to Use - Analyzing workflows that do NOT use any AI agent actions (use general Actions security tools instead) …
Read the whole file at its exact version.
How to install
mdr add trailofbits/skills/agentic-actions-auditor@sha256:b2bdb88d559bc37eThe line at the top of this page pins the label git:20260831.9645e2f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_qghc3rftqn4ye73j)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Feb 26, 2026 and Aug 31, 2026, about one every 93 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260831.9645e2f latest | 2026-08-31 | 9645e2f | 21,743 B | A | view · diff |
| git:20260428.debfb29 | 2026-04-28 | debfb29 | 21,526 B | A | view · diff |
| git:20260226.ed41cd7 | 2026-02-26 | ed41cd7 | 21,542 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (21743 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
trailofbits/skills · 7,698 stars · license CC-BY-SA-4.0 · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qghc3rftqn4ye73j GET https://markdownregistry.com/api/v1/resolve?ref=trailofbits/skills/agentic-actions-auditor GET https://markdownregistry.com/api/v1/blob/b2bdb88d559bc37e6c2c8314e28e7a2eb47e7cdd9da51e77da347d3517326dc0
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from trailofbits/skills
Every file in trailofbits/skills