prd
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided ideas and context to generate PRDs written to the local file system.
- Ingestion points: User input gathered during the discovery phase and initial context as defined in SKILL.md.
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within user input.
- Capability inventory: Writing generated content to the file path prd/PRD.md.
- Sanitization: There are no specified methods for sanitizing user-provided text before it is written to disk.
- [NO_CODE]: The skill is comprised entirely of markdown instructions for the AI agent and does not include any executable scripts or software dependencies.
Audit Metadata