llm-models
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides documentation and usage examples for the 'belt' CLI tool to interact with LLMs via OpenRouter. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected.
- [EXTERNAL_DOWNLOADS]: The skill references the vendor's own CLI installation guide on GitHub ('github.com/inference-sh/skills') and links to the vendor's official website ('inference.sh'). These are legitimate vendor resources and do not represent a security risk.
- [COMMAND_EXECUTION]: The skill demonstrates the use of the 'belt' CLI tool for logging in and running LLM applications. These commands are restricted to the 'belt' executable as defined in the skill's frontmatter configuration.
Audit Metadata