visant-video-editor

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes ffmpeg and ffprobe extensively to perform video and audio manipulation. These commands are executed locally on media provided by the user and are strictly for processing tasks such as rendering, normalization, and metadata extraction.
  • [EXTERNAL_DOWNLOADS]: Mentions legitimate third-party tools such as faster-whisper and auto-editor as requirements. These are well-established libraries in the media processing community and are used here for their intended purposes.
  • [DYNAMIC_EXECUTION]: Employs Python scripts and shell loops to manage complex editing workflows. The use of subprocess.run in scripts/plan.py and the execution of Python code via heredocs in scripts/transcribe.sh are implemented using best practices to avoid shell injection and are confined to the task of media transcription and planning.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No evidence of unauthorized data access or network communication was found. File operations are confined to the source and project directories provided by the user via environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 04:42 PM