video-prompting-guide

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides examples of using the belt CLI tool to authenticate (belt login) and execute video generation models (e.g., belt app run google/veo-3-1-fast). This is standard operational use of the vendor's platform.
  • [EXTERNAL_DOWNLOADS]: References installation instructions and documentation hosted on the official GitHub repository for the vendor (raw.githubusercontent.com/inference-sh/skills).
  • [SAFE]: All external resources, domains (inference.sh), and tools (belt-sh/cli) originate from the verified vendor infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 04:34 AM
Security Audit — agent-trust-hub — video-prompting-guide