← Back to Skills Marketplace
tankebuaa

Web Browsing

by tankebuaa · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
12906
Downloads
9
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install web-browsing
Description
Browse and summarize websites, extract content from URLs, search the web for information. Use when user asks to visit a website, get webpage content, search...
Usage Guidance
Install only if you are comfortable with the agent sending your search terms and provided URLs to external services. Do not use it with secrets, private/internal URLs, credentials in query strings, or sensitive personal data unless the runtime has strong outbound network controls. The publisher should add URL validation, redirect revalidation, private-network blocking, download limits, and clear privacy disclosure before this is treated as low-risk.
Capability Assessment
⚠ Credentials
Network access is proportionate for a browsing skill, but unrestricted outbound fetching from the agent runtime is under-scoped because it may reach localhost, private-network, link-local, metadata, or redirected destinations.
✓ Install Mechanism
No install hooks, package-install commands, tool replacement, or automatic setup behavior were found; the artifact ships a markdown skill, a usage guide, and one helper script.
⚠ Instruction Scope
The instructions clearly describe broad web search and URL-fetch behavior, but they do not define a permission boundary or warn users that queries and URLs are sent to external services and target sites.
✓ Persistence & Privilege
No persistence, credential access, session/profile use, privilege escalation, memory modification, scheduled task, or background worker behavior was found.
⚠ Purpose & Capability
Searching the web and fetching pages are aligned with the stated web-browsing purpose, but fetch_url accepts arbitrary caller-provided URLs, follows redirects, and returns page content without destination validation.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install web-browsing
  3. After installation, invoke the skill by name or use /web-browsing
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the web-browsing skill. - Enables browsing and summarizing websites, extracting content from URLs, and searching the web for information. - Provides tools for web search, direct URL content retrieval, and HTML content extraction. - Includes guidelines and best practices for effective use. - Outlines current limitations, including handling of dynamic sites and login-required pages.
Metadata
Slug web-browsing
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Web Browsing?

Browse and summarize websites, extract content from URLs, search the web for information. Use when user asks to visit a website, get webpage content, search... It is an AI Agent Skill for Claude Code / OpenClaw, with 12906 downloads so far.

How do I install Web Browsing?

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

Is Web Browsing free?

Yes, Web Browsing is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Web Browsing support?

Web Browsing is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Web Browsing?

It is built and maintained by tankebuaa (@tankebuaa); the current version is v1.0.0.

💬 Comments