davinci-resolve-computer-use-training

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the subprocess module to execute local system commands and media utilities. These include ps for environment diagnostics (checking if DaVinci Resolve is running), ffmpeg for generating test audio assets, and ffprobe for analyzing media file durations. These operations are essential for the skill's primary function of media automation.
  • [COMMAND_EXECUTION]: The skill includes a bash wrapper (bin/resolve-kit) and Python orchestration scripts (e.g., capstone_folder_pipeline.py) that invoke other internal scripts to manage multi-step project staging and validation workflows.
  • [SAFE]: An installation script (install_resolve_kit.py) copies utility scripts into the standard DaVinci Resolve user scripts directory on macOS. This is a legitimate and documented method for extending Resolve's functionality via the 'Workspace > Scripts' menu.
  • [SAFE]: The skill relies on the official DaVinci Resolve Python/Lua scripting API to perform project management, media import, and timeline editing. It correctly manages environment variables and system paths to interface with the locally installed software SDK.
  • [SAFE]: References to the author's domain (chaiwithjai.com) are used for documentation and as a target for manual content preparation, with no automated network exfiltration or suspicious communication detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 12:07 PM
Security Audit — agent-trust-hub — davinci-resolve-computer-use-training