eval
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves a legitimate purpose for code evaluation and does not exhibit any malicious behaviors such as data exfiltration, persistence, or obfuscation.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted code changes for evaluation.
- Ingestion points: The skill ingests 'git diff' data, build outputs, and file references through the 'evaluator' sub-agent.
- Boundary markers: The prompt instructions lack explicit delimiters or instructions to ignore embedded commands within the code being analyzed.
- Capability inventory: The skill is restricted to a limited toolset including
Read,Bash,Grep, andGlob. - Sanitization: The skill does not implement sanitization or filtering of the code content it evaluates.
Audit Metadata