skills/vm0-ai/vm0-skills/computer-use/Gen Agent Trust Hub

computer-use

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses okou computer-use to perform various GUI actions such as listing apps, opening apps, reading application state, and simulating user input (clicks, typing, key presses). These are the primary functions of the skill and operate within the expected environment of the Zero Desktop host.
  • [COMMAND_EXECUTION]: Node.js and rg (ripgrep) are used to process and filter JSON output from the CLI tool. This is a standard way to handle large accessibility trees and does not involve dynamic execution of untrusted code or remote scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 09:35 PM
Security Audit — agent-trust-hub — computer-use