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.
Profile →npx skills add sickn33/agentic-awesome-skills --skill agentic-actions-auditor --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Static security analysis guidance for GitHub Actions workflows that invoke AI coding agents. It 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.
How it works
- It guides you to determine analysis mode (local vs remote) based on input like a GitHub repository URL.
- It instructs fetching workflow files from .github/workflows using gh api commands and processing YAML content.
- It requires scanning workflow files to identify steps with uses: values that reference AI actions such as anthropics/claude-code-action, google-github-actions/run-gemini-cli, google-gemini/gemini-cli-action, openai/codex-action, and actions/ai-inference.
- For each matched step, it records file path, job name, step name or id, full uses: value, and action type.
- It includes cross-file resolution to examine composite actions and reusable workflows one level deep.
- It then captures security-relevant information per action type from the with: block (e.g., prompts, settings, model, token) and workflow-level context (trigger events, env blocks, permissions).
- Finally, it outlines a structured audit and findings process, though it does not execute or modify workflows itself.
When to use it
- When auditing a repository's GitHub Actions workflows for AI agent security
- When reviewing CI/CD configurations that invoke Claude Code Action, Gemini CLI, or OpenAI Codex
- When checking whether attacker-controlled input can reach AI agent prompts
- When evaluating agentic action configurations (sandbox settings, tool permissions, user allowlists)
- When assessing trigger events that expose workflows to external input (pull_request_target, issue_comment, etc.)
- When investigating data flow from GitHub event context through env: blocks to AI prompt fields
What it can touch
- The guidance references AI action usage within workflow files, with fields in with: blocks for Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. It also considers env: blocks, on: triggers, and permissions within the workflow context.
Caveats
- This is static analysis guidance and not a run-time exploit or remediation tool. It reports findings and does not modify workflow files.
- Evaluation depends on the presence of AI action references in workflow YAML and on accurate cross-file resolution limited to one level deep.
# 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 standalo
- When to Use
- When NOT to Use
- Rationalizations to Reject
- Audit Methodology
- Step 0: Determine Analysis Mode
- Step 1: Discover Workflow Files
- Step 2: Identify AI Action Steps
- Step 3: Capture Security Context
- Step 4: Analyze for Attack Vectors
- Step 5: Report Findings
- Detailed References
- Limitations
What does the agentic-actions-auditor skill do?
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.
How do I install it?
Run `npx skills add sickn33/agentic-awesome-skills --skill agentic-actions-auditor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From sickn33/agentic-awesome-skills, a repository with 44,414 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.