video-watch

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The scripts scripts/video_watch.py and scripts/preflight.py utilize subprocess.run to execute external binaries including ffmpeg, ffprobe, and yt-dlp. These executions are essential for the skill's primary functionality of video metadata extraction and frame sampling. The commands are constructed using argument lists, which mitigates the risk of shell injection.\n- [EXTERNAL_DOWNLOADS]: The skill facilitates the download of video content and transcripts from remote URLs using yt-dlp. The implementation includes a dedicated function warn_sensitive_url that inspects URL query strings for common credential keys (e.g., tokens, signatures) and issues a warning if found, demonstrating proactive security design.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 08:11 AM
Security Audit — agent-trust-hub — video-watch