agentic-actions-auditor
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a detailed and structured methodology for auditing GitHub Actions workflows for security risks. It focuses on static analysis and data flow tracking from GitHub event contexts to AI agent prompts.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and processing untrusted data (remote GitHub workflow files). The author has included specific 'Bash Safety Rules' in Step 0 that instruct the agent to never execute or pipe fetched content to interpreters (bash, python, node, etc.), effectively mitigating the risk of executing malicious payloads contained within the audited files.
- [COMMAND_EXECUTION]: The skill uses standard GitHub CLI commands (
gh api) to list and fetch repository contents. These commands are necessary for the skill's stated purpose of auditing remote repositories and do not involve unauthorized or dangerous system modifications. - [REMOTE_CODE_EXECUTION]: No patterns of downloading and executing arbitrary scripts or installing unverified dependencies were detected. The instructions prioritize safe data handling and provide clear boundaries for tool usage.
Audit Metadata