scenario-gemini-omni
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and usage examples for the Scenario platform. It does not contain scripts, executables, or commands that perform sensitive file access, credential harvesting, or unauthorized network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill outlines workflows for processing external assets (images, videos) and user prompts through the Gemini Omni models. While this ingestion process presents a theoretical surface for indirect prompt injection—where instructions could be hidden in visual media—the skill interacts exclusively with platform-specific tools (
model_run,upload_asset) and does not introduce unsafe data interpolation into system commands or sensitive contexts.
Audit Metadata