po
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a persona and coordinator for project management tasks. It does not contain any executable code, network operations, or sensitive data access. Findings across all analyzed threat categories are negative.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: Reads project artifacts including PRDs (prd.md), architecture designs (architecture.md), and user stories defined in the workspace.
- Boundary markers: None explicitly defined to isolate or ignore instructions embedded within the processed documents.
- Capability inventory: The skill is an orchestrator that invokes other tools (review-story, execute-checklist, correct-course, shard-doc) but does not have direct access to shell execution or network requests.
- Sanitization: No explicit sanitization or filtering of external document content is implemented. Validation logic relies on predefined checklists.
Audit Metadata