write-a-prd
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as intended for a documentation tool, using standard repository exploration and local file creation patterns without malicious intent.
- [PROMPT_INJECTION]: The skill is subject to a potential indirect prompt injection surface because it processes untrusted data from the local codebase.
- Ingestion points: Local repository files are read during the exploration phase (Step 2).
- Boundary markers: Absent; the instructions do not explicitly tell the agent to ignore instructions that might be found within the files it explores.
- Capability inventory: The skill has the capability to write files to the 'docs/prd/' directory (Step 5).
- Sanitization: Absent; content derived from the codebase and user interview is interpolated directly into the PRD template.
Audit Metadata