Browser Automation
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
Why this rating
Deterministic checks triggered by the tool capabilities and evidence.
- Locality: Hybrid
Uses local Chrome or a remote Browserbase environment and navigates user-provided URLs.
- Data access: Sensitive
Can extract page content and take screenshots while interacting with web apps (including sign-in flows).
- Action surface: Execute
Runs CLI-driven browser commands (`navigate`, `act`, `extract`, `screenshot`) that can click/type/submit on sites.
Best practices
Follow these steps to reduce risk when using this skill.
- Use a dedicated browser profile and avoid logging into high-value accounts unless necessary.
- Verify each step with `browser screenshot` and prefer `browser observe` before clicking/typing.
- Store Browserbase keys in `.env`, rotate/revoke if exposed, and close the browser (`browser close`) when finished.
Evidence links
Public sources backing the indicator assignments.
Always be careful when navigating away from the website.
Max-risk rule
If any capability reaches a higher level, the entire indicator level bumps up to keep ratings deterministic and easy to scan.