Skills
skills/skillssh/skills/ai-avatar-video/Gen Agent Trust Hub

ai-avatar-video

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool to execute AI models for video generation. Access is restricted via the allowed-tools manifest to the belt command space, which is appropriate for the skill's functionality.
  • [EXTERNAL_DOWNLOADS]: The instructions point to official installation scripts and documentation hosted on the inference-sh GitHub organization and inference.sh domain. These are standard resources required for the skill's intended operation.
  • [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. The skill uses external URLs for image and audio inputs, which are standard parameters for the AI generation models being utilized.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 08:39 AM
Security Audit — agent-trust-hub — ai-avatar-video