llm-models
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation scripts and additional skill components hosted on the official inference-sh GitHub repository.
- [REMOTE_CODE_EXECUTION]: Uses the
belt app runcommand to execute logic and model inferences hosted on the inference.sh platform, which is the core functionality of the service. - [COMMAND_EXECUTION]: Employs the
beltCLI for operational tasks including authentication, model search, and execution, with tool access restricted to this specific CLI by the skill configuration.
Audit Metadata