Evidence-first video reading for AI agents — ffprobe, subtitles, scenes, transcripts, and timelines without frame-by-frame LLM vision.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
Evidence-first video reading for AI agents — ffprobe, subtitles, scenes, transcripts, and timelines without frame-by-frame LLM vision.