llm-models
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the 'belt-sh/cli' and 'inference-sh/skills' packages using the npx command. These are official components for the service described.
- [COMMAND_EXECUTION]: The skill provides examples for using the 'belt' CLI tool to run inference tasks, search for applications, and manage login sessions. All command execution is scoped to the specific CLI tool defined in the allowed-tools configuration.
- [DATA_EXPOSURE_&_EXFILTRATION]: The skill includes instructions for 'belt login', which is a standard procedure for authenticating a CLI tool with its service provider. No unauthorized data exfiltration patterns were detected.
Audit Metadata