Curl Search for Openclaw

A security-hardened, multi-engine web search skill that leverages curl and Python for lightweight online data retrieval.

bluejoy34
v2.0.0
Mar 14, 2026
1
1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install curlsearch

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install curlsearch using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Curl Search?

Curl Search is a powerful addition to the ecosystem of Openclaw Skills, designed to provide AI coding agents with direct access to global search engines without requiring expensive or complex API keys. By utilizing curl and Python 3, this skill enables agents to fetch information from Baidu, Google, Bing, and DuckDuckGo through a lightweight, command-line interface. It serves as an essential fallback or primary search mechanism for developers who need fast, scriptable web access within their AI workflows.

The skill prioritizes security and reliability, implementing robust input sanitization and protection against command injection. Whether you are building an agent for research or automating data gathering, Curl Search offers a versatile and privacy-conscious way to integrate search functionality into your environment using the standards of Openclaw Skills.

Curl Search Use Cases

  • Executing web queries for technical documentation or tutorials directly through an AI agent.
  • Retrieving search results from specific regions using engines like Baidu or Google.
  • Automating research tasks when dedicated search APIs are unavailable or cost-prohibitive.
  • Integrating privacy-focused searches via DuckDuckGo into automated workflows.

How Curl Search Works

  1. The AI agent receives a user prompt requesting a web search or online lookup.
  2. The input query is processed through a sanitization layer to remove dangerous shell characters and prevent command injection.
  3. A Python-based URL encoder formats the query string safely for HTTP requests.
  4. The skill executes a curl command targeting the selected search engine (Baidu, Google, Bing, or DDG).
  5. The resulting search data is returned to the agent for further processing or presentation to the user.

Curl Search Setup

To install this skill through the official Openclaw Skills repository:

# Install via ClawHub
clawhub install curl-search

Manual installation:

cd your-skills-dir
tar -xzf curl-search.tar.gz

Configuration via environment variables:

# Set the default search engine (options: bd, g, b, ddg)
export SEARCH_ENGINE=google

# Limit the number of results returned (1-50)
export MAX_RESULTS=5

Curl Search Data Schema & Taxonomy

The skill utilizes environment variables for configuration and handles search data through standard output. Below is the metadata taxonomy:

Variable Type Description
SEARCH_ENGINE String The alias for the preferred engine (bd, g, b, ddg).
MAX_RESULTS Integer Maximum results to fetch (Default: 5).
input_sanitization Boolean Internal security check for shell metacharacters.
url_encoding Boolean Python-based encoding for query safety.

Curl Search Advanced Features

  • Multi-engine aliasing for fast switching between regional search providers.
  • Hardened security layer featuring shell metacharacter filtering to prevent exploits.
  • Intelligent URL encoding using Python's urllib to ensure query integrity across engines.
  • Support for high-concurrency environments through lightweight curl processes.
  • Integration compatibility with other Openclaw Skills for complex multi-agent research pipelines.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*