aqe-review-quality
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified. The skill's primary function is to enhance the quality and security of code through a rigorous review process.
- [COMMAND_EXECUTION]: The instructions enable the agent to execute focused commands to verify claims made in the code under review. This is an intended feature for its role as a quality assurance tool.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted user data (code diffs and implementations) and has the capability to execute commands. In the context of a quality engineering tool, this is a functional requirement.
- Ingestion points: SKILL.md instructions read user-provided diffs, code, and tests.
- Boundary markers: The skill does not define explicit delimiters to isolate untrusted content from the agent's instructions.
- Capability inventory: SKILL.md grants the agent the ability to run focused shell commands for verification.
- Sanitization: No sanitization of the reviewed content is specified before processing or command execution.
Audit Metadata