duck-review
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and generates text-based code reviews. It does not request access to any tools or perform any actions outside of generating text responses.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code provided by users, which represents a potential attack surface for indirect prompt injection. However, the security risk is effectively mitigated by the skill's lack of executable capabilities.
- Ingestion points: User-supplied code, diffs, and pull request text described in SKILL.md.
- Boundary markers: Not explicitly implemented in the prompt instructions.
- Capability inventory: The skill is explicitly restricted from modifying files, approving changes, or executing commands in the Boundaries & Handoffs section of SKILL.md.
- Sanitization: Input data is not sanitized, which is considered safe due to the absence of tools that could be abused by malicious code in the input.
Audit Metadata