agentic-actions-auditor SKILL.md skillA
agentic-actions-auditor from gsa-tts/agentic-coding-patterns is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gsa-tts/agentic-coding-patterns/agentic-actions-auditor@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gsa-tts/agentic-coding-patterns
- Path
.agents/skills/agentic-actions-auditor/SKILL.md- Versions recorded
- 3
- Latest version
- v1.0.0, committed Aug 20, 2026
- First version recorded
- Jul 2, 2026
- Size
- 12,026 bytes
- Repository stars
- 16
- License
- CC0-1.0
Audit CI/CD workflows that invoke LLM agents for dangerous trigger, checkout, token-scope, and prompt-construction patterns — flags the injection and blast-radius surface without shipping a working exploit.
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
# Skill: Agentic Actions Auditor Audit CI/CD workflows that **invoke an LLM agent** for the patterns that turn a pipeline into an attacker-reachable action surface: dangerous event triggers, untrusted checkout of pull-request code with secrets in scope, over-scoped `GITHUB_TOKEN`, agent prompts built from attacker-controlled text, and missing human-approval gates before the agent writes or takes irreversible actions. > **This skill is self-limiting.** It audits agent-invoking CI for dangerous > trigger, checkout, permission, and prompt-construction patterns; it describes > each pattern and its fix but ships **no working end-to-end exploit**. Minimal > YAML snippets that show a dangerous trigger are config patterns, not payloads, > and each is paired with the safer form. Authoritative policy lives in the > [agentic-coding-playbook](https://github.com/GSA-TTS/agentic-coding-playbook); > this skill defers all policy there and never restates it. ## When to Use - Reviewing a GitHub Actions (or similar CI) workflow that calls an LLM agent — a code reviewer bot, an issue triager, an auto-fixer, or a chat-ops agent …
Read the whole file at its exact version.
How to install
mdr add gsa-tts/agentic-coding-patterns/agentic-actions-auditor@sha256:a04e73eee95db9acThe line at the top of this page pins the label v1.0.0, 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_edb37mqqjbcdcx77)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 2, 2026 and Aug 20, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-08-20 | ae5b0dd | 12,026 B | A | view · diff |
| v1.0.0 | 2026-07-28 | ea6ea67 | 12,023 B | A | view · diff |
| v1.0.0 | 2026-07-02 | c736287 | 11,453 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 (12026 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
gsa-tts/agentic-coding-patterns · 16 stars · license CC0-1.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_edb37mqqjbcdcx77 GET https://markdownregistry.com/api/v1/resolve?ref=gsa-tts/agentic-coding-patterns/agentic-actions-auditor GET https://markdownregistry.com/api/v1/blob/a04e73eee95db9acea027875a80c22e562a2cbf01193dd041fbdeeb7994dd779
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 gsa-tts/agentic-coding-patterns
Every file in gsa-tts/agentic-coding-patterns