happyhorse
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and examples for interacting with video generation models via the
beltCLI tool. All behaviors identified are consistent with the skill's primary purpose. - [EXTERNAL_DOWNLOADS]: Fetches installation guidelines and configuration details from the inference-sh organization's public GitHub repository. This is standard behavior for integrating with the inference.sh platform.
- [COMMAND_EXECUTION]: Demonstrates the use of the
beltcommand-line interface to run remote AI applications. The scope of shell execution is appropriately restricted to thebelttool via theallowed-toolsconfiguration in the skill metadata.
Audit Metadata