code-review-checklist
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions designed to influence the agent's review output.
- Ingestion points: The skill explicitly requests the user to provide "PR description" and "Code or diff" in
SKILL.md. - Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore prompt injection attempts embedded within the code comments or PR descriptions.
- Capability inventory: The skill is designed to produce text-based checklists and decision frameworks; it does not contain instructions for file system modifications, network exfiltration, or automated command execution.
- Sanitization: There are no instructions for the agent to sanitize or filter the input data before processing it for the checklist generation.
Audit Metadata