net-new-video-editor

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/net_new_video_editor.py invokes ffmpeg and ffprobe for media analysis and rendering. These calls use the subprocess module with list-based arguments, effectively preventing shell injection.
  • [SAFE]: Path security is maintained by a dedicated inside() helper function that resolves and validates all file paths against the project root, preventing directory traversal vulnerabilities.
  • [SAFE]: Caption rendering is handled through the Pillow library, which rasterizes text into images before compositing with FFmpeg. This avoids the security risks associated with passing user-provided text directly into complex FFmpeg filters.
  • [SAFE]: The skill enforces strict type validation for numerical parameters (dimensions, timestamps, audio levels) extracted from JSON plans, ensuring they are valid numbers before processing.
  • [COMMAND_EXECUTION]: The SKILL.md contains preamble instructions to execute optional telemetry scripts if they exist in a parent environment. While these files are not bundled with the skill, the execution pattern is handled gracefully and does not introduce a vulnerability in the skill's own code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 01:56 AM
Security Audit — agent-trust-hub — net-new-video-editor