From file to useful result
How to ask with this skill installed
Installing the skill gives your AI a method. Your request still has to provide the case-specific facts, constraints and expected output.
1Name the real task
Describe the decision or deliverable, not just the topic.
2Provide the evidence
Add source material, audience, limits and known facts.
3Define done
Set format, quality criteria and checks.
Adaptable starting prompt
Replace the brackets with your case
When to use it
- 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 it
- 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)