Skills
Navigate
skills/zenithth/anibon-stream-synthesis/edit-cut-video-ffmpeg/Gen Agent Trust Hub

edit-cut-video-ffmpeg

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides command templates for ffmpeg and yt-dlp to be executed in a shell environment.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates downloading video segments from external URLs using the yt-dlp utility.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection and command injection through the processing of untrusted input.
  • Ingestion points: Untrusted data enters the agent context via the 'URL' parameter in the yt-dlp command within SKILL.md.
  • Boundary markers: There are no boundary markers or instructions to sanitize or escape the 'URL' variable before interpolation.
  • Capability inventory: The skill utilizes subprocess calls to yt-dlp and ffmpeg (found in SKILL.md).
  • Sanitization: No sanitization, escaping, or validation logic is defined for the external input provided to the command line arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 04:56 AM
Security Audit — agent-trust-hub — edit-cut-video-ffmpeg