Skills
skills/inference-skills/skills/ai-video-generation/Gen Agent Trust Hub

ai-video-generation

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt command-line interface (e.g., belt app run, belt app store) to interact with remote AI models. This execution is scoped by the allowed-tools frontmatter restriction.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation, images, and installation scripts hosted on the vendor's official domain (inference.sh) and GitHub organization (inference-sh). These are legitimate resources for the skill's functionality.
  • [DATA_EXPOSURE]: The skill allows the agent to pass user-provided prompts and media URLs (images, audio, video) to the vendor's API for processing. This is the primary intended function of the generative AI service.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 09:05 AM
Security Audit — agent-trust-hub — ai-video-generation