LaunchKit · 2026
Back to Skills

Headless browser automation with Tor SOCKS5 proxy support for accessing .onion sites and anonymous browsing.

0
409 downloads
by @admin4giter

Setup & Installation

openclaw skills install @admin4giter/tor-browser

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install tor-browser

Version History

v1.1.0Feb 20, 2026 - Version note by skill developer:

v1.1.0: Added new features, improved stability, bug fixes

What This Skill Does

Headless browser automation routed through the Tor network for accessing .onion sites and anonymous web browsing. Supports navigation, element interaction, screenshots, and link extraction via CLI commands or a Python API.

Routes Playwright automation through Tor natively, removing the need to configure system-wide proxies or manage separate browser profiles for anonymized requests.

When to use it

  • Scraping data from Tor hidden services
  • Taking screenshots of .onion pages for threat intelligence reports
  • Checking accessibility of a .onion site you operate
  • Automating form interactions on dark web forums for security research
  • Extracting links from hidden service directories

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: extract all links from a .onion search engine

AGENT
  1. 1Run `tor-browser check-tor` to verify the Tor connection is active
  2. 2Navigate to the .onion URL with `tor-browser open http://3g2upl4pq6kufc4m.onion`
  3. 3Run `tor-browser links` to extract all hyperlinks from the loaded page
  4. 4Pipe the output to a file for further analysis
OUTPUT

A list of URLs and anchor text found on the hidden service page

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

Tor service installed and running with SOCKS5 proxy on port 9050 (`sudo apt install tor && sudo systemctl start tor`)Playwright Chromium browser (`playwright install chromium`)