get-prd
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user answers during the interview rounds and writes that content into a PRD file, which may be read by other automated tools.
- Ingestion points: User answers and reactions gathered during Phase 3 (Round Questions) and Phase 4 (Intent Probe) as defined in SKILL.md.
- Boundary markers: The skill does not implement or instruct the use of delimiters or specific security warnings when interpolating user content into the PRD template.
- Capability inventory: The skill possesses the capability to write files to the local filesystem at
docs/prd/(referenced in Phase 7 of SKILL.md). - Sanitization: There are no instructions to sanitize, escape, or validate the user-provided text before it is saved to the project documentation.
Audit Metadata