code-review-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of markdown instructions and metadata. It does not contain any code, binary files, or external network calls. It promotes security best practices by including security verification steps in the generated checklists.
- [INDIRECT_PROMPT_INJECTION]: The skill operates on external, untrusted data (code diffs), which presents a potential injection surface. However, the risk is mitigated by the limited read-only capability of the tools used.
- Ingestion points: PR diffs and codebase files accessed through Read, Grep, and Glob tools (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters to differentiate between system instructions and user-provided code data.
- Capability inventory: The skill is restricted to Read, Grep, and Glob tools, preventing any system modification or network exfiltration.
- Sanitization: There are no specific instructions for the agent to sanitize or escape data found within the files it reviews.
Audit Metadata