claude-video-shorts

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local bash scripts and utilizes FFmpeg for media processing. These operations are essential for its purpose of extracting and editing video clips.\n- [EXTERNAL_DOWNLOADS]: The documentation references standard Python packages such as whisperx, scenedetect, google-genai, mediapipe, and opencv-python. These are reputable libraries used for media processing and AI.\n- [CREDENTIALS_UNSAFE]: The skill mentions the requirement of a GOOGLE_API_KEY environment variable. This is a standard and safe method for managing API credentials for external services like Gemini Flash.\n- [DATA_EXFILTRATION]: Video frames are sent to Google's Gemini API for visual analysis. This is a core feature of the pipeline and utilizes a well-known, trusted service. No other unexpected network activity was identified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 02:55 PM
Security Audit — agent-trust-hub — claude-video-shorts