Skills
skills/qu-skills/skills/p-video-avatar/Gen Agent Trust Hub

p-video-avatar

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external installation documentation for the belt CLI tool hosted on a public GitHub repository (github.com/inference-sh).
  • [COMMAND_EXECUTION]: The skill provides examples of using the belt CLI via system commands to interact with remote AI models for video and image generation.
  • [PROMPT_INJECTION]: The parameter documentation suggests a default value of true for disable_safety_filter, which is a configuration to bypass content filtering for the generated avatar videos.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 07:03 PM
Security Audit — agent-trust-hub — p-video-avatar