receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill defines behavioral constraints that forbid the agent from using social niceties like gratitude or blind agreement. These instructions are intended to enforce technical rigor and professional distance, and do not constitute an attempt to bypass safety or security guidelines.
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves processing untrusted external feedback from code reviews, which presents an attack surface for indirect prompt injection.
- Ingestion points: External review feedback and comments entering the agent's context during the code review response process.
- Boundary markers: The instructions do not specify the use of delimiters (such as XML tags or special tokens) to isolate the untrusted external content.
- Capability inventory: The skill utilizes
gitandgh(GitHub CLI) for codebase verification and API interactions, and is designed to trigger implementation through other skills. - Sanitization: No programmatic sanitization is defined; however, the skill mandates a skepticism-first verification workflow ('Verify before implementing', 'Ask before assuming') which serves as a manual validation process to prevent the adoption of malicious or erroneous suggestions.
Audit Metadata