image-to-video

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill mentions and provides a link to an installation script for the belt CLI tool from a known repository (https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md). Per standard rules, this is documented neutrally as a functional requirement for the skill's purpose.
  • [COMMAND_EXECUTION]: The skill provides numerous examples of how to use the belt command-line interface to interact with various AI models (e.g., belt app run falai/wan-2-5-i2v). These are standard operational instructions for the tool described in the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides advice on how to structure prompts for image-to-video models. It includes a section on 'The Golden Rule: Subtle > Dramatic' to prevent artifacts, which is a common best practice in generative AI interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 11:00 PM
Security Audit — agent-trust-hub — image-to-video