prd-doc-writer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied product requirements and feedback to generate documentation, which represents a standard data ingestion surface.
- Ingestion points: User input provided during the conversational PRD drafting process, specifically in the "Detail the Stories" phase (SKILL.md).
- Boundary markers: The skill employs a strict "Three-step confirmation" workflow, requiring explicit user approval for the journey map, individual user stories, and the final document generation gate to prevent unintended output.
- Capability inventory: The skill's capabilities are limited to generating text, ASCII wireframes, and Mermaid diagrams; it does not use network tools, shell execution, or sensitive file system access.
- Sanitization: The interactive confirmation loop acts as a human-in-the-loop validation step, ensuring all content is reviewed by the user before the final PRD is generated using the template in
assets/prd-template.md.
Audit Metadata