prd-requirements-verifier
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain instructions designed to subvert the verification process.
- Ingestion points: The agent is instructed to read external PRD files and project implementation changes in SKILL.md.
- Boundary markers: Absent. There are no instructions or delimiters provided to help the agent distinguish between requirements data and potentially malicious instructions embedded within the PRD.
- Capability inventory: The instructions direct the agent to "Use the strongest available evidence: automated tests, project checks, code inspection, or manual testing," which implies the ability to execute shell commands and read local files (SKILL.md).
- Sanitization: Absent. The skill does not provide mechanisms to filter or sanitize the content of the documents being verified.
Audit Metadata