p-video-avatar

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation references an installation script for the belt CLI hosted on the vendor's official GitHub repository (inference-sh/skills). This is a legitimate resource for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill uses the belt command-line interface to interact with the Pruna P-Video-Avatar model. Shell access is restricted to this specific tool via the allowed-tools configuration.
  • [PROMPT_INJECTION]: The skill includes a disable_safety_filter parameter. This is a standard configuration option for the specific model API being used and does not represent an attempt to hijack or bypass the agent's core safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 08:36 PM