p-video-avatar
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
beltCLI (viaBash(belt *)allowed-tools) to interact with remote AI models. These commands are standard for the tool's purpose and follow best practices for CLI interaction. - [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation and an installation script from
github.com/inference-sh, which is a recognized service provider for this tool. These references are informative and represent the intended installation path. - [DATA_EXPOSURE]: The skill includes an optional parameter
disable_safety_filterset totruein documentation examples. While this disables content moderation on the remote server, it is a documented feature of the specific AI model and does not expose local system data.
Audit Metadata