requirements-clarity
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input during the initial requirement analysis and the subsequent interactive clarification rounds (SKILL.md, Steps 1 and 3).
- Ingestion points: The skill parses the user's initial requirement description and captures information from follow-up clarification answers.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat user-provided data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill uses a Write tool to save the generated PRD to the local filesystem at ./docs/prds/.
- Sanitization: There are no mentioned mechanisms for sanitizing or escaping the user-provided content before it is interpolated into the PRD document.
Audit Metadata