@peytoncasper

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.

当前版本
v1.0.1
47 3.5万总安装 466

name: browser 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. allowed-tools: Bash

Browser Automation

Automate browser interactions using Stagehand CLI with Claude.

First: Environment Selection (Local vs Remote)

The skill automatically selects between local and remote browser environments:

  • If Browserbase API keys exist (BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID in .env file): Uses remote Browserbase environment
  • If no Browserbase API keys: Falls back to local Chrome browser
  • No user prompting: The selection happens automatically based on available configuration

Setup (First Time Only)

Check setup.json in this directory. If setupComplete: false:

npm install    # Install dependencies
npm link       # Create global 'browser' command

Commands

All commands work identically in both modes:

browser navigate <url>                    # Go to URL
browser act "<action>"                    # Natural language action
browser extract "<instruction>" ['{}']    # Extract data (optional schema)
browser observe "<query>"                 # Discover elements
browser screenshot                        # Take screenshot
browser close                             # Close browser

Quick Example

browser navigate https://example.com
browser act "click the Sign In button"
browser extract "get the page title"
browser close

Mode Comparison

FeatureLocalBrowserbase
SpeedFasterSlightly slower
SetupChrome requiredAPI key required
Stealth modeNoYes
Proxy/CAPTCHANoYes
Best forDevelopmentProduction/scraping

Best Practices

  1. Always navigate first before interacting
  2. View screenshots after each command to verify
  3. Be specific in action descriptions
  4. Close browser when done

Troubleshooting

  • Chrome not found: Install Chrome or use Browserbase mode
  • Action fails: Use browser observe to discover available elements
  • Browserbase fails: Verify API key and project ID are set

For detailed examples, see EXAMPLES.md. For API reference, see REFERENCE.md.

Security Scan

状态

suspicious

打开 VirusTotal

OpenClaw

gpt-5-mini

suspicious

OpenClaw 分析

The skill's documentation describes a browser automation CLI that needs an AI model key and optionally remote service keys and a local Chrome profile, but the package metadata omits those requirements and the actual code is not included — these mismatches and privacy implications are concerning.

置信度: medium

VirusTotal

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.

元数据

  • 作者: @peytoncasper
  • 创建时间: 2026/02/05
  • 更新时间: 2026/04/13
  • 版本数: 2
  • 评论数: 3
  • 扫描时间: 2026/02/11

运行要求

官方公开数据里暂未列出运行要求。