explainer-video-guide

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the belt CLI and related skills from the inference-sh repository. These references are standard for the toolset described and target the developer's official distribution channels.
  • [COMMAND_EXECUTION]: Multiple examples demonstrate how to use the belt utility for generating media. These shell commands are limited to the specific tool authorized in the skill's configuration, following the principle of least privilege.
  • [PROMPT_INJECTION]: The skill processes user-generated prompts within belt app run commands in SKILL.md. While no specific boundary markers or sanitization steps are defined for these inputs, the capabilities are limited to media generation via external models that implement their own safety filters. This indirect injection surface is inherent to the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:04 AM
Security Audit — agent-trust-hub — explainer-video-guide