← Back to Skills Marketplace
lnblxj

Web Search Local

by lnblxj · GitHub ↗ · v0.1.1 · MIT-0
cross-platform ✓ Security Clean
229
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install web-search-local
Description
Local web search without API Key. Supports Bing, DuckDuckGo, Yandex multi-engine search with built-in cache and automatic failover. Use when users need to se...
Usage Guidance
This skill appears coherent for local web scraping search. Before installing: (1) be aware it performs live HTTP(S) requests to public search engines (Bing, DDG, Yandex) and may trigger CAPTCHAs or be blocked in some networks; (2) it stores cached search results under ~/.cache/web-search-local (inspect or clear with --cache-clear if you care about local storage); (3) install the documented Python dependencies (requests, beautifulsoup4) manually or in a virtualenv; (4) verbose/debug logs may include queries and timing info—avoid using with sensitive queries if you don't want them logged; (5) if you require stronger isolation, run the script in a sandboxed container or VM. If you want greater assurance, review the full scripts/search.py file for any additional network calls or behavior not covered in the docs (the provided file looks consistent with the documented functionality).
Capability Analysis
Type: OpenClaw Skill Name: web-search-local Version: 0.1.1 The web-search-local skill is a functional utility designed to perform web searches across multiple engines (Bing, DuckDuckGo, Yandex) without requiring an API key. The core logic in `scripts/search.py` implements standard scraping techniques, including RSS/HTML parsing, random delays, and user-agent rotation to avoid bot detection. It features a local file-based cache in `~/.cache/web-search-local/` and supports proxy configurations, both of which are consistent with its stated purpose. No evidence of data exfiltration, malicious command execution, or prompt injection was found in the code or documentation.
Capability Assessment
Purpose & Capability
Name/description match the implementation: the code scrapes search engines, supports engine selection/auto-failover, caching, delays and proxy options. There are no extraneous credential or system access requests that don't belong to a web-search tool.
Instruction Scope
SKILL.md and code consistently instruct the agent to run the provided CLI script and document its flags. Instructions and code operate on network requests and a local cache directory (~/.cache/web-search-local) only; they do not attempt to read unrelated system files or external secrets.
Install Mechanism
There is no declared install spec in the registry (instruction-only), but the README and docs state runtime dependencies (requests, beautifulsoup4). That mismatch (no automated install step) is not malicious but worth noting: the agent or user must install dependencies manually.
Credentials
The skill requests no environment variables, no credentials, and only writes to its own cache directory in the user's home. Proxy configuration is supported via CLI/API functions; that is appropriate for a network client. No unrelated secrets (AWS keys, tokens) are required.
Persistence & Privilege
Skill does not request persistent 'always' inclusion, does not modify other skills, and only stores its own cache files under ~/.cache/web-search-local. It does not alter system-wide agent configuration or other skill settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install web-search-local
  3. After installation, invoke the skill by name or use /web-search-local
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.1
- Added sample documentation files: README.md, docs/engine-expansion.md. - Introduced main search script: scripts/search.py. - No changes to core functionality; new files provide additional documentation and usage guidance.
v0.1.0
Initial release of web-search-local: local web search without API key, supporting multiple engines and built-in caching. - Supports Bing, DuckDuckGo, Yandex, and a urllib-based fallback with automatic failover. - No API key required; works locally with triggers for common search commands in English and Chinese. - Built-in caching for faster repeated queries; cache can be managed from the command line. - Flexible output in JSON or text format; supports saving results to a file. - Command-line options for engine selection, result limitation, performance tuning, and verbose logging.
Metadata
Slug web-search-local
Version 0.1.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Web Search Local?

Local web search without API Key. Supports Bing, DuckDuckGo, Yandex multi-engine search with built-in cache and automatic failover. Use when users need to se... It is an AI Agent Skill for Claude Code / OpenClaw, with 229 downloads so far.

How do I install Web Search Local?

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

Is Web Search Local free?

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

Which platforms does Web Search Local support?

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

Who created Web Search Local?

It is built and maintained by lnblxj (@lnblxj); the current version is v0.1.1.

💬 Comments