← Back to Skills Marketplace
peytoncasper

Browser Automation

by peytoncasper · GitHub ↗ · v1.0.1
cross-platform ⚠ suspicious
46826
Downloads
62
Stars
544
Active Installs
2
Versions
Install in OpenClaw
/install browser-automation
Description
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.
Usage Guidance
Install only if you can inspect and trust the actual CLI package that `npm install` and `npm link` will expose. Use a dedicated browser profile and test accounts, explicitly choose local versus remote mode, avoid sensitive sites unless necessary, clear stored profile data when done, and manually confirm any form submission, account change, download, or scraping workflow.
Capability Analysis
Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill The skill is classified as suspicious due to several high-risk capabilities, even though it does not explicitly instruct malicious actions. The `SKILL.md` explicitly allows the `Bash` tool, granting the AI agent arbitrary command execution. The `REFERENCE.md` details that the browser has 'full network access' and uses a 'persistent profile (`.chrome-profile/`)' which can store 'saved passwords and cookies,' creating a potential vector for credential access or exfiltration if combined with Bash commands. Additionally, the skill can download arbitrary files to `./agent/downloads/`, which could then be executed by the agent using the allowed Bash tool.
Capability Assessment
Purpose & Capability
The stated purpose of navigating websites, clicking, extracting data, screenshots, and form filling is coherent with the browser automation capabilities, but the scope covers arbitrary sites, authenticated sessions, downloads, and scraping-style remote use.
Instruction Scope
The skill allows Bash and directs use of natural-language browser actions without a clear confirmation boundary before logins, form submissions, account-impacting clicks, or downloads.
Install Mechanism
The setup instructs `npm install` and `npm link` to create a global `browser` command, but this artifact set contains only documentation and setup metadata, not the referenced package source or `package.json` needed to verify what will be installed.
Credentials
Remote Browserbase mode is disclosed, but the skill says it switches automatically when Browserbase keys exist and does not require an explicit user opt-in before browsing activity and form inputs may use remote infrastructure.
Persistence & Privilege
Persistent `.chrome-profile/` storage, saved cookies/passwords, automatic screenshots, automatic downloads to `./agent/downloads/`, and full network access including localhost/internal networks are documented, but they are high-impact and under-controlled.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install browser-automation
  3. After installation, invoke the skill by name or use /browser-automation
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Initial public release
v1.0.0
- Initial release of browser automation skill. - Automates web browser interactions using Stagehand CLI and natural language commands. - Supports both local Chrome and remote Browserbase environments; selection is automatic based on configuration. - Provides commands for navigation, interaction, extraction, element observation, screenshots, and closing the browser. - Includes troubleshooting tips and setup instructions for both environments.
Metadata
Slug browser-automation
Version 1.0.1
License
All-time Installs 1588
Active Installs 544
Total Versions 2
Frequently Asked Questions

What is 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. It is an AI Agent Skill for Claude Code / OpenClaw, with 46826 downloads so far.

How do I install Browser Automation?

Run "/install browser-automation" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Browser Automation free?

Yes, Browser Automation is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Browser Automation support?

Browser Automation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Browser Automation?

It is built and maintained by peytoncasper (@peytoncasper); the current version is v1.0.1.

💬 Comments