loop-on-ci
Pass
Audited by Gen Agent Trust Hub on May 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub Action logs (
gh run view --log-failed) and PR check statuses (gh pr checks). - Ingestion points: External data enters the agent context through CI logs and PR check metadata.
- Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: The agent is empowered to diagnose failures and push code fixes based on the logs it reads.
- Sanitization: The skill does not mention specific sanitization for log content.
- [COMMAND_EXECUTION]: The skill uses standard GitHub CLI (
gh) commands to interact with the repository's CI/CD pipeline. These are well-known tools used for their intended purpose in a developer workflow.
Audit Metadata