gemini-omni-flash-api
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill integrates with the official
google-genaiSDK to facilitate video generation and editing via Gemini models. - [COMMAND_EXECUTION]: The provided Python scripts execute
ffmpegandffprobefor media processing tasks such as trimming, resizing, and metadata inspection. These commands are executed using list-based arguments without a shell, which is a secure practice for the skill's primary function. - [EXTERNAL_DOWNLOADS]: The skill fetches generated video files from
generativelanguage.googleapis.com. This is a verified and trusted Google API endpoint used for media delivery. - [SAFE]: The codebase implements path validation logic within the
safe_user_pathfunction to mitigate potential path traversal risks during local file operations.
Audit Metadata