skills/varghq/skills/video-animate/Gen Agent Trust Hub

video-animate

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/take_check.py uses subprocess.run to securely invoke ffmpeg and ffprobe for video metadata analysis. The implementation correctly passes arguments as a list and does not use shell=True, preventing command injection risks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external video and JSON data for technical validation purposes. Evidence Chain: (1) Ingestion points: take.mp4 and previz.mp4 in scripts/take_check.py. (2) Boundary markers: Not present for technical data extraction. (3) Capability inventory: Local binary execution via subprocess.run. (4) Sanitization: Secure argument passing in Python.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with vendor infrastructure at varg.ai for API services and references reputable filmmaking databases. These network calls target trusted author-controlled endpoints and legitimate industry resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 09:50 PM