gemini
Pass
Audited by Gen Agent Trust Hub on Nov 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and examples for using the
beltCLI tool to interact with Google Gemini models. All external links point to the officialinference.shdomain or standard documentation repositories. The tool usage is constrained to theBashtool with thebeltcommand, which is the intended purpose of the skill. No malicious patterns, such as prompt injection, unauthorized data access, or obfuscation, were found.
Audit Metadata