← Back to Skills Marketplace
Browser Use
by
shawn pana
· GitHub ↗
· v2.0.1
· MIT-0
51583
Downloads
106
Stars
470
Active Installs
5
Versions
Install in OpenClaw
/install browser-use
Description
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with w...
Usage Guidance
Install only if you need a powerful browser automation bridge and trust the external browser-use CLI. Prefer isolated or throwaway browser profiles, avoid syncing profiles to cloud, do not export or print cookies unless you explicitly intend to handle session secrets, confirm any file upload/account-changing action, and stop tunnels plus close browser sessions when finished.
Capability Analysis
Type: OpenClaw Skill
Name: browser-use
Version: 2.0.1
The bundle provides a powerful browser automation toolset with several high-risk capabilities, including arbitrary Python execution via `browser-use python` and JavaScript execution via `browser-use eval`. It also features commands for exporting session cookies, accessing the user's local Chrome profiles, and establishing network tunnels (`browser-use tunnel`). While these functions are consistent with the stated purpose of advanced web automation and testing, they represent a significant security risk as they could be easily leveraged for data exfiltration or host compromise. Files: SKILL.md, references/cdp-python.md.
Capability Assessment
Purpose & Capability
The browser automation purpose is coherent, and most capabilities are disclosed, but the documented surface extends into high-impact areas: existing Chrome profiles with preserved logins/cookies, cookie import/export, file upload, JavaScript eval, raw Python/CDP access, cloud REST passthrough, public tunnels, and profile sync to cloud.
Instruction Scope
The instructions explain how to perform sensitive actions but provide limited approval boundaries. They tell the agent to ask which Chrome profile to use for authenticated browsing, but do not similarly gate cookie extraction/export, profile sync, cloud REST passthrough, tunnels, file uploads, or raw CDP/Python use.
Install Mechanism
The artifact is instruction-only and allows Bash(browser-use:*), relying on an external browser-use CLI that is not included or pinned in the reviewed files. Static scan reported no suspicious patterns in the skill files themselves.
Credentials
Using real Chrome profiles, preserved logins/cookies, cloud profile sync, and Cloudflare tunnels is powerful and sometimes useful for web testing, but the artifact does not sufficiently scope these capabilities to isolated profiles, specific domains, safe ports, or explicit per-use consent.
Persistence & Privilege
Persistent browser daemons, multi-session sockets, cloud persistent profiles, saved API keys, config storage, and active tunnels are disclosed, and cleanup commands are documented, but users must actively close sessions and stop tunnels.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install browser-use - After installation, invoke the skill by name or use
/browser-use - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.1
- Added two new reference documents: CDP Python usage and multi-session workflows.
- Clarified the distinction between headless mode, connecting to Chrome, and cloud browser usage.
- Made tab management commands (`tab list`, `tab new`, `tab switch`, `tab close`) explicit in documentation.
- Improved explanations for cloud connection, API key registration, and agent self-registration.
- Added instructions for multi-session (parallel browser) usage.
- Updated troubleshooting guidance for failed commands and session cleanup.
v2.0.0
- Improved and reorganized documentation for clarity and modern workflows.
- Added details on using named Chrome profiles, connecting to running Chrome via CDP, and cloud browser workflows.
- Documented command chaining for efficient multi-step automation.
- Included guidance for authenticated browsing, local tunnels, and profile management.
- Clarified command options, output handling, and best practices for stateful session management.
v1.0.2
- Documentation reworked and simplified for clarity and easier reference.
- Audience broadened: Skill now addresses general browser automation, not just sandboxed/cloud use.
- Install modes, tunnel setup, and environment variable explanations are removed for a more concise guide.
- New dedicated sections for browser modes, session management, essential commands, and Python execution.
- Updated and better-organized CLI command reference.
- Usage examples and options for real/Chromium/cloud browsers are clarified with practical guidance.
- For full advanced setup details, directs users to the official README.
v1.0.1
**Changelog for browser-use v1.0.1**
- Updated documentation to focus on running browser-use from sandboxed, remote environments (cloud VMs, CI, remote coding agents).
- Added instructions for remote-only install, removing the need to download Chromium locally.
- Clarified usage of cloud browser as the default in remote-only mode; `browser-use open <url>` uses remote session automatically.
- Expanded and reorganized CLI command documentation, including navigation, interaction, state, tunneling, and Python session usage.
- Provided step-by-step guidance for exposing remote dev servers via Cloudflare tunnels.
- Added comprehensive command references for tab management, cookies, waits, and agent tasks.
- Emphasized remote/sandbox mode as core for agents with no GUI access.
v1.0.0
Initial release of browser-use skill for Clawdbot:
- Adds integration with Browser Use cloud API to create and manage remote browser sessions, supporting persisted cookies and profiles.
- Enables autonomous browser tasks via a subagent using a fast, browser-optimized LLM.
- Provides simple setup and usage instructions, including API key configuration and pricing details.
- Includes documentation links and cURL request examples for sessions, profiles, and task automation.
Metadata
Frequently Asked Questions
What is Browser Use?
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with w... It is an AI Agent Skill for Claude Code / OpenClaw, with 51583 downloads so far.
How do I install Browser Use?
Run "/install browser-use" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Browser Use free?
Yes, Browser Use is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Browser Use support?
Browser Use is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Browser Use?
It is built and maintained by shawn pana (@shawnpana); the current version is v2.0.1.
More Skills