browser-use
SKILL.md
Browser-Use — AI Browser Automation
Security & Privacy
- No credential logging: Passwords are handled via Browser-Use's
sensitive_dataparameter — the LLM never sees real credentials, only placeholder tokens. - User-initiated Chrome connection: CDP mode (connecting to real Chrome) is opt-in and requires the user to manually launch Chrome with debug flag. The skill never silently connects to running browsers.
- All packages are open-source: Dependencies are
browser-use(38k+ ⭐ on GitHub),playwright(by Microsoft), andlangchain-openai— all widely audited open-source tools. - Local execution only: Scripts run locally on the user's machine. No data is sent to any server except the configured LLM API for step-by-step reasoning.
- Domain restriction available: Use
allowed_domainsparameter to restrict which websites the agent can visit. - No telemetry: This skill does not collect, store, or transmit any usage data.
When to Use Browser-Use vs Built-in Tool
| Scenario | Built-in tool | Browser-Use |
|---|---|---|
| Screenshot / click one button | ✅ Free & fast | ❌ Overkill |
| 5+ step workflow (login→navigate→fill→submit) | ❌ Breaks easily | ✅ |
| Anti-bot sites (real Chrome needed) | ❌ | ✅ |
| Batch repetitive operations | ❌ | ✅ |