qa-review
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its design as a code and documentation reviewer.
- Ingestion points: Untrusted data enters the agent context via user-provided git diffs, pull request descriptions, and code snippets, as specified in the 'Expected Inputs' section of
SKILL.md. - Boundary markers: The skill lacks instructions for using delimiters or boundary markers to isolate the untrusted code from the agent's analysis instructions.
- Capability inventory: The skill acts as a gatekeeper with the authority to approve or reject changes. While it does not define its own tools, it operates within the agent's environment which typically includes file system and version control capabilities.
- Sanitization: There are no instructions for the agent to validate or sanitize the input data before performing the audit.
Audit Metadata