paperclip-converting-plans-to-tasks
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied plans which constitutes an ingestion point for untrusted data. However, it implements boundary strategies by recommending the use of specific issue IDs for dependencies rather than prose, and requires a verification step (re-fetching issues) before closing planning tasks. Given that this is a core functional requirement for task management, the surface risk is minimal and controlled within the application framework.
- [SAFE]: The skill consists entirely of instructional markdown. It does not perform network operations, access sensitive local files (such as SSH keys or environment variables), or attempt to execute remote scripts. It provides clear guidance on respecting permission boundaries (e.g., handling 403 errors for low-trust reviewers).
Audit Metadata