← Back to Skills Marketplace
Agent Browser Skill
by
baiyunrei2025
· GitHub ↗
· v1.0.0
· MIT-0
383
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install agent-browser-skill
Description
Automate web browsing with navigation, form filling, clicking, screenshots, data extraction, and testing using Chrome via OpenClaw browser tool.
README (SKILL.md)
Agent Browser Skill
Description
Enhanced browser automation for OpenClaw agents with advanced navigation, screenshot, and interaction capabilities.
When to Use
Use this skill when:
- Automating web browsing tasks
- Taking screenshots of web pages
- Filling forms and clicking buttons
- Extracting data from websites
- Testing web applications
- Navigating complex web flows
Prerequisites
- OpenClaw browser tool must be enabled
- Chrome or Chromium browser installed
- Internet connection for web access
Examples
Basic Navigation
# Navigate to a website
openclaw browser open --url "https://example.com"
# Take a screenshot
openclaw browser snapshot --url "https://example.com" --output screenshot.png
Form Interaction
# Fill a form
openclaw browser act --url "https://forms.example.com" --kind fill --fields '{"name": "John", "email": "[email protected]"}'
# Click a button
openclaw browser act --url "https://example.com" --kind click --selector "button.submit"
Data Extraction
# Extract page content
openclaw browser snapshot --url "https://news.example.com" --maxChars 5000
# Monitor page changes
openclaw browser act --url "https://status.example.com" --kind wait --textGone "Loading..."
Integration with OpenClaw
This skill enhances the native OpenClaw browser tool with:
- Simplified commands - Easier syntax for common tasks
- Error handling - Better recovery from failures
- Performance optimization - Faster page loads and interactions
- Accessibility support - Better element detection
Safety Notes
- Only automate public websites
- Respect robots.txt and terms of service
- Avoid excessive requests to prevent IP blocking
- Use delays between actions to mimic human behavior
Troubleshooting
Common Issues
- Browser not starting: Check if Chrome is installed
- Element not found: Try different selectors or wait for page load
- Timeout errors: Increase timeout values for slow pages
- Permission denied: Ensure OpenClaw has necessary permissions
Debug Tips
# Enable verbose logging
openclaw browser open --url "https://example.com" --verbose
# Check browser status
openclaw browser status
References
Usage Guidance
This skill appears to do what it claims: it builds shell commands that call the local OpenClaw browser CLI. Before installing or enabling it, consider: 1) The included script uses child_process.exec and concatenates user-supplied values into shell commands — if the agent is ever given untrusted input that becomes an argument, a malicious string could perform command injection. Prefer running this skill only with trusted inputs or replacing exec with a safer API (spawn/execFile with arg arrays) or sanitizing inputs. 2) The skill will drive a browser and therefore can access any content the browser can — avoid visiting pages with secrets or auto-submitting sensitive forms. 3) Verify the OpenClaw browser tool/CLI on your system is the legitimate implementation you expect. 4) If you will run the skill in a shared environment, sandbox it (network / filesystem restrictions) or review and modify scripts to harden argument handling. If you need, I can suggest concrete code changes to remove shell interpolation and use a safer child_process pattern.
Capability Analysis
Type: OpenClaw Skill
Name: agent-browser-skill
Version: 1.0.0
The skill bundle contains a significant command injection vulnerability in `scripts/browser-automation.js`. The `executeCommand` function constructs shell commands by concatenating arguments into a string passed to `child_process.exec` without proper sanitization or escaping. While the script's stated purpose is browser automation, this flaw allows for arbitrary code execution if malicious input is provided to the command arguments. No evidence of intentional malice or data exfiltration was found.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md, and the included script all focus on driving the OpenClaw browser tool (open, snapshot, act, etc.). There are no unrelated environment variables, binaries, or config paths requested; the requested capabilities are proportional to a browser automation helper.
Instruction Scope
SKILL.md confines runtime instructions to calling the OpenClaw browser tool and gives examples, safety guidance, and troubleshooting steps. It does not instruct reading unrelated files, harvesting environment variables, or sending data to external endpoints outside the expected browser interactions.
Install Mechanism
There is no install spec (instruction-only). However, the package includes a JavaScript wrapper (scripts/browser-automation.js) which will be written to disk when the skill is installed. The script uses child_process.exec to run CLI commands; no remote downloads or extract steps are present.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. The code does not read environment variables. This matches the described purpose.
Persistence & Privilege
always is false and model invocation is allowed (platform default). The skill does not request permanent presence or attempt to modify other skills or system-wide configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-browser-skill - After installation, invoke the skill by name or use
/agent-browser-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Agent Browser Skill 1.0.0 introduces advanced browser automation for OpenClaw agents.
- Provides simplified commands for navigation, screenshots, form interactions, and data extraction.
- Enhances error handling and performance for faster and more reliable web automation.
- Adds accessibility improvements for better element detection.
- Includes best practices, troubleshooting tips, and usage examples for common tasks.
- Requires Chrome or Chromium and an active OpenClaw browser tool.
Metadata
Frequently Asked Questions
What is Agent Browser Skill?
Automate web browsing with navigation, form filling, clicking, screenshots, data extraction, and testing using Chrome via OpenClaw browser tool. It is an AI Agent Skill for Claude Code / OpenClaw, with 383 downloads so far.
How do I install Agent Browser Skill?
Run "/install agent-browser-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent Browser Skill free?
Yes, Agent Browser Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Agent Browser Skill support?
Agent Browser Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent Browser Skill?
It is built and maintained by baiyunrei2025 (@baiyunrei2025); the current version is v1.0.0.
More Skills