review-testing
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code files, which is a standard surface for indirect prompt injection.
- Ingestion points: The skill reads changed test files and associated production code as defined in the 'Review Scope' section of SKILL.md.
- Boundary markers: No specific delimiters or 'ignore' instructions are provided for handling the code content.
- Capability inventory: The instructions involve reading files and potentially applying fixes, indicating the agent has file read and write capabilities.
- Sanitization: No input sanitization is specified for the code being reviewed.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or malicious command execution was found. The skill's external references are limited to its own documentation on GitHub, which is a resource owned by the vendor.
Audit Metadata