task-planning
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill body consists of instructional guidelines for implementation planning and does not contain any malicious patterns, obfuscation, or persistence mechanisms.
- [DATA_EXFILTRATION]: The skill references Paperclip platform API endpoints (/api/issues/) for managing plan documents and comments. These are legitimate vendor resources owned by 'paperclipai' and are central to the skill's intended functionality.
- [PROMPT_INJECTION]: The skill ingests external issue data to generate plans, creating a surface for indirect prompt injection. However, no high-risk capability abuse or safety bypass patterns were identified. Ingestion point: Paperclip issues. Boundary markers: None. Capability inventory: Platform API access for issue documents and comments. Sanitization: None specified.
Audit Metadata