code-review
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources such as pull requests and code diffs.
- Ingestion points: Untrusted data enters the agent context through 'PR, diff, or local changes' as described in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the text.
- Capability inventory: The skill has no dangerous capabilities. It is explicitly limited to 'Review only' and instructs the agent to 'Never perform a mutation test or edit files' without user confirmation.
- Sanitization: There is no evidence of input validation or sanitization for the code being reviewed.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill adheres to best practices by requiring user confirmation for any file modifications and focusing strictly on analysis.
Audit Metadata