video-creator

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions and recipes for executing ffmpeg commands and Python-based video scripts. This command execution is essential for the skill's intended function of video creation and editing.
  • [EXTERNAL_DOWNLOADS]: The skill mentions 'yt-dlp' for fetching video content and 'pip' for installing the 'faster-whisper' library. These references are to well-known tools and repositories in the technology ecosystem.
  • [PROMPT_INJECTION]: The skill processes external media files and content from URLs, creating a surface for indirect prompt injection. This is an inherent characteristic of media processing tools.
  • Ingestion points: Media files processed by ffmpeg and content downloaded via 'yt-dlp' from external URLs.
  • Boundary markers: None identified in the instructions for isolating external content from the agent's control flow.
  • Capability inventory: Media processing via ffmpeg/ffprobe subprocesses and script execution for video compositing.
  • Sanitization: The skill does not explicitly describe sanitization of metadata or untrusted data contained within media assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 02:40 AM
Security Audit — agent-trust-hub — video-creator