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 belt CLI (via Bash(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_filter set to true in 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
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — p-video-avatar