web-search
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation guides and images from the vendor's own GitHub repository (inference-sh) and domain (inference.sh), which is standard for documentation and setup.
- [COMMAND_EXECUTION]: Functional commands are restricted to the 'belt' CLI tool through the 'allowed-tools' configuration in the frontmatter, limiting the agent's shell access to the intended application.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized credential access was found. The skill follows best practices by providing structured JSON input examples for CLI operations.
Audit Metadata