pre-mortem
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill defines a specialized persona for product management tasks and does not contain any suspicious logic or commands.- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any scripts, executables, or dependency installations.- [PROMPT_INJECTION]: The skill is designed to ingest and process external documents (PRDs), which presents a surface for indirect prompt injection. However, the limited capabilities of the agent mitigate this risk. (1) Ingestion points: User-provided PRD or product plan files. (2) Boundary markers: Absent. (3) Capability inventory: Writing markdown files to disk and performing web searches. (4) Sanitization: Absent.
Audit Metadata