loop-or-not
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill examines standard project configuration files (e.g., package.json, Makefile, CI workflows) and GitHub metadata (issues, PRs). This data access is aligned with the skill's purpose of discovering candidate tasks and existing verification tools within a development environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issue and PR descriptions. The design mitigates potential injection risks by implementing a 'human-in-the-loop' interview phase where the user must review, confirm, and manually finalize the agent's drafted automation contracts.
- [EXTERNAL_DOWNLOADS]: The skill references community-regarded educational repositories and vendor-owned tutorial materials for guidance. These are informative links and do not involve automated execution of external code or unverified downloads.
Audit Metadata