product-specifier
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (product ideas) to generate a structured PRD file, creating an indirect prompt injection surface. The risk is considered minimal as the skill's purpose is document generation and it includes manual clarification steps.
- Ingestion points: User-provided product ideas and clarification answers.
- Boundary markers: Absent; user input is directly interpolated into the reasoning process.
- Capability inventory: File system write access to create the
specs/PRD.mdfile. - Sanitization: Absent; the skill relies on LLM interpretation of the user input.
Audit Metadata