agentic-actions-auditor

agentic-actions-auditor is a skill for Claude Code from waybarrios/opencode-power-pack. It costs 44 tokens per session (4,671 once invoked), scanned A, a copy of agentic-actions-auditor, MIT.

A security review guide for GitHub Actions workflows that run AI coding agents. GitHub Actions is GitHub's system for automatically running tasks such as tests and deployments.

In plain words
What is it for?
Use it to inspect agent-enabled workflows, follow reusable workflow and action references, trace event data into prompts, and check triggers, permissions, and user restrictions.
Why use it?
It helps identify prompt-injection paths, unsafe use of untrusted event data, weak sandbox settings, and overly broad permissions before an agent runs in CI.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Part of the opencode-power-pack plugin — 54 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/waybarrios/opencode-power-pack/agentic-actions-auditor
Any agent
npx skills add waybarrios/opencode-power-pack --skill agentic-actions-auditor
Clone the repo
git clone --depth 1 https://github.com/waybarrios/opencode-power-pack

Made for: Claude Code.

Or install opencode-power-pack, the plugin that ships this one along with the rest of its 54 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agentic-actions-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/waybarrios/opencode-power-pack/agentic-actions-auditor.svg)](https://agentmods.dev/skills/waybarrios/opencode-power-pack/agentic-actions-auditor)
Your own site
<a href="https://agentmods.dev/skills/waybarrios/opencode-power-pack/agentic-actions-auditor"><img src="https://agentmods.dev/badge/skills/waybarrios/opencode-power-pack/agentic-actions-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,671 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 92% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.04671
Opus 5 $0.00022 $0.02336
Sonnet 5 $0.00009 $0.00934
Haiku 4.5 $0.00004 $0.00467

Measured 6d ago against content hash aef91fc6243e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agentic-actions-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

92% identical to agentic-actions-auditor — 54 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/agentic-actions-auditor/SKILL.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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)
  • Reviewing standalone composite actions or reusable workflows outside of a caller workflow context (use this skill when analyzing a workflow that references them via uses:)
  • Performing runtime prompt injection testing (this is static analysis guidance, not exploitation)
  • Auditing non-GitHub CI/CD systems (Jenkins, GitLab CI, CircleCI)
  • Auto-fixing or modifying workflow files (this skill reports findings, does not modify files)

Rationalizations to Reject

When auditing agentic actions, reject these common rationalizations. Each represents a reasoning shortcut that leads to missed findings.

1. "It only runs on PRs from maintainers" Wrong because it ignores pull_request_target, issue_comment, and other trigger events that expose actions to external input. Attackers do not need write access to trigger these workflows. A pull_request_target event runs in the context of the base branch, not the PR branch, meaning any external contributor can trigger it by opening a PR.

Read the full file on GitHub · 324 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 324 lines · 44 tokens per session scan A aef91fc6243e

Subscribe to this mod's changes

agentic-actions-auditor is a skill published in the GitHub repository waybarrios/opencode-power-pack (490 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 4,671 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to agentic-actions-auditor, differing in 54 lines, and is treated as a copy.

Related

Other skills, from other repositories

council-gate

Quality gate using LLM Council multi-model consensus for CI/CD pipelines. Use for automated approval workflows and pipeline quality checks. Keywords: gate, CI, CD, pipeline, automated approval, quality gate, GitHub Actions.

amiable-dev/llm-council · 50 tokens

ci-triage

Diagnose and fix red CI on zaxy — fetch the right logs, reproduce locally despite the known local quirks (testdoctor hang, benchmark tables), do coverage-ratchet math correctly, and apply the test-vs-source intent rule. Use when CI is red, a check fails on a PR, "make master green", or coverage ratchet fails.

syndicalt/zaxy · 79 tokens

test_engineer

Test Engineer Persona for building and maintaining the testing infrastructure.

sachinshelke/ToolsConnector · 11 tokens

setup-ci

Teaches CI/CD from first principles to a non-developer, then scaffolds a working test + deploy pipeline. Handles the common hosts (GitHub Actions, GitLab CI, CircleCI, Travis, Jenkins) and common deploy targets (SSH to VM, Vercel, Netlify, Fly.io, Cloud Run, Docker registries). Asks what the operator has before…

subinium/vibesubin · 85 tokens

debug-ci

Use when CI/CD pipeline fails. Provides systematic diagnosis for lint, type, test, and build failures across Python, TypeScript, Java, Rust, and n8n SDKs.

open-metadata/ai-sdk · 40 tokens

ci-failure-triage

Use when make ci-local fails locally or a GitHub Actions run reports a CI failure (format, lint, line-budget, typecheck, or test errors).

berntpopp/mgi-link · 41 tokens