ai-video-generation

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides links to installation instructions and documentation hosted on the vendor's official GitHub repository (inference-sh/skills) and primary domain (inference.sh). These are standard resources for the service provided.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool via Bash commands to facilitate AI video generation tasks. This execution is scoped to the belt tool as defined in the skill's frontmatter and aligns with its primary purpose.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it accepts user-provided text prompts and external media URLs (image, audio, video) which are then processed by remote AI models. While this is inherent to the function of a media generation tool, it represents a path where untrusted data enters the processing pipeline.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 12:55 AM
Security Audit — agent-trust-hub — ai-video-generation