gemini-omni

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of documentation providing instructions on how to use the Gemini Omni model through standard platform tools. No executable code or malicious patterns were identified.
  • [EXTERNAL_DOWNLOADS]: The skill contains references to official Google AI documentation and blog posts (ai.google.dev and blog.google), which are trusted sources and do not present a security risk.
  • [INDIRECT_PROMPT_INJECTION]: While the skill explains how to prompt an AI model with user-provided text and files, it does not implement a vulnerable pipeline. The instructions focus on legitimate creative use cases for video generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 08:42 AM