fix-github-actions
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
ghandgitCLI tools to retrieve pull request status, list workflow runs, download logs, and manage branch state. These commands are standard for the skill's stated purpose of CI/CD debugging. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of GitHub Actions workflow logs. While these logs originate from external execution environments and could contain untrusted content, the risk is mitigated by the skill's specific focus on parsing logs for technical errors (linting, testing, building) rather than executing instructions found within them.
- Ingestion points: GitHub Actions logs retrieved via
gh run view --log-failed. - Boundary markers: None explicitly defined in instructions.
- Capability inventory: File reading, file writing, git commit/push, and gh CLI operations.
- Sanitization: Relies on the agent's internal reasoning to differentiate between log data and instructions.
Audit Metadata