skills/xixu-me/skills/use-my-browser/Gen Agent Trust Hub

use-my-browser

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on policy and strategy rather than providing executable scripts with hidden payloads. It teaches the agent how to evaluate the necessity of browser use to minimize intrusion.
  • [SAFE]: All external references and prerequisites direct users to legitimate resources, such as official Google Chrome developer blogs and established Chrome DevTools documentation.
  • [SAFE]: The session management guidelines explicitly instruct the agent to avoid destructive behaviors like closing or reloading user-owned tabs and to prefer non-intrusive data extraction methods (DOM snapshots) over visual ones.
  • [SAFE]: The installation and configuration instructions use standard package management patterns (npx/bunx) to run recognized tools such as the Chrome DevTools MCP server.
  • [SAFE]: The tool escalation logic (starting with public web searches and only moving to a live browser if necessary) adheres to the principle of least privilege by using the least sensitive tool first.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 07:19 PM