prd-writer
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains only markdown-based instructions for document creation and does not include any scripts or code. There are no mechanisms for command execution or remote data access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input to generate PRDs, creating a theoretical injection surface. 1. Ingestion points: Inputs include stakeholder briefs, competitive research, and feature requests provided in plain language. 2. Boundary markers: No delimiters or instructions to ignore embedded commands are present. 3. Capability inventory: The skill has no tool permissions or execution capabilities. 4. Sanitization: There is no sanitization or validation of the ingested data. Assessment: The lack of execution capabilities renders the risk of indirect injection negligible.
Audit Metadata