gemini-omni-flash-api

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run to execute ffmpeg and ffprobe for video processing tasks like inspecting metadata, stripping audio, and re-encoding. This is a legitimate requirement for the skill's media processing capabilities.
  • Evidence found in scripts/video/generate_video.py, scripts/video/inspect_video.py, scripts/video/prep_video.py, and scripts/upload_file.py.
  • [EXTERNAL_DOWNLOADS]: The skill connects to official Google Gemini API endpoints (generativelanguage.googleapis.com) to upload media assets and download generated video results.
  • Evidence found in scripts/video/generate_video.py and scripts/upload_file.py.
  • [REMOTE_CODE_EXECUTION]: One script optionally executes another local Python script (prep_video.py) using sys.executable. This is used as part of the video pre-processing workflow and is restricted to the local filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 02:57 PM
Security Audit — agent-trust-hub — gemini-omni-flash-api