Searxng — 技能 — openclaw中文资讯站

技能详情（站内镜像，无评论）

Privacy-respecting metasearch using your local SearXNG instance. Search the web, images, news, and more without external API dependencies.

媒体与内容

作者：Avinash Venkatswamy @abk234

许可证：MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本：v1.0.3

统计：⭐ 25 · 13.7k · 310 current installs · 330 all-time installs

⭐ 25

安装量（当前） 330

🛡 VirusTotal ：良性 · OpenClaw ：良性

Package：abk234/searxng

安全扫描（ClawHub）

VirusTotal ：良性
OpenClaw ：良性

OpenClaw 评估

The skill's code and instructions match its stated purpose (local SearXNG metasearch); small documentation/metadata inconsistencies and an SSL verification decision are the only notable issues.

目的

The skill is a CLI wrapper around a local SearXNG JSON API. Required binary (python3) and included script are consistent with the description. No unrelated cloud credentials, binaries, or config paths are requested.

说明范围

SKILL.md and the script only call the SearXNG HTTP API and print results. They do not read other system files or try to exfiltrate secrets. Note: the instructions and script expect a SEARXNG_URL environment variable (defaulting to http://localhost:8080) — the SKILL.md emphasizes configuring this.

安装机制

No install spec is provided (instruction-only), so nothing is downloaded or executed automatically. The bundle does include a Python script that lists dependencies (httpx, rich) in its header; those are normal for a CLI skill but are not auto-installed by the registry.

证书

The skill requires a SEARXNG_URL to operate, which is appropriate. Registry metadata at the top lists 'Required env vars: none' while SKILL.md/metadata indicate SEARXNG_URL is required — this mismatch is a documentation/metadata inconsistency that should be fixed. No sensitive credentials are requested.

持久

The skill is not always-enabled and does not request elevated or persistent privileges. It does not modify other skills or system-wide settings. Agent autonomous invocation is allowed (platform default) but not combined with any broad credentials or persistence.

综合结论

This skill appears to do exactly what it claims: query a SearXNG instance and display results. Before installing: 1) Ensure SEARXNG_URL points to a trusted instance (local or a public instance you trust); queries go to that host. 2) If you connect to a remote instance, edit the script to enable SSL verification (change verify=False) — the current default disables SSL verification and suppresses warnings to support self-signed certs, which incr…

安装（复制给龙虾 AI）

将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Searxng」。简介：Privacy-respecting metasearch using your local SearXNG instance. Search the web…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/abk234/searxng/SKILL.md
（来源：yingzhi8.cn 技能库）

SKILL.md

打开原始 SKILL.md（GitHub raw）

---
name: searxng
description: Privacy-respecting metasearch using your local SearXNG instance. Search the web, images, news, and more without external API dependencies.
author: Avinash Venkatswamy
version: 1.0.1
homepage: https://searxng.org
triggers:
  - "search for"
  - "search web"
  - "find information"
  - "look up"
metadata: {"clawdbot":{"emoji":"🔍","requires":{"bins":["python3"]},"config":{"env":{"SEARXNG_URL":{"description":"SearXNG instance URL","default":"http://localhost:8080","required":true}}}}}
---

# SearXNG Search

Search the web using your local SearXNG instance - a privacy-respecting metasearch engine.

## Commands

### Web Search
```bash
uv run {baseDir}/scripts/searxng.py search "query"              # Top 10 results
uv run {baseDir}/scripts/searxng.py search "query" -n 20        # Top 20 results
uv run {baseDir}/scripts/searxng.py search "query" --format json # JSON output
```

### Category Search
```bash
uv run {baseDir}/scripts/searxng.py search "query" --category images
uv run {baseDir}/scripts/searxng.py search "query" --category news
uv run {baseDir}/scripts/searxng.py search "query" --category videos
```

### Advanced Options
```bash
uv run {baseDir}/scripts/searxng.py search "query" --language en
uv run {baseDir}/scripts/searxng.py search "query" --time-range day
```

## Configuration

**Required:** Set the `SEARXNG_URL` environment variable to your SearXNG instance:

```bash
export SEARXNG_URL=https://your-searxng-instance.com
```

Or configure in your Clawdbot config:
```json
{
  "env": {
    "SEARXNG_URL": "https://your-searxng-instance.com"
  }
}
```

Default (if not set): `http://localhost:8080`

## Features

- 🔒 Privacy-focused (uses your local instance)
- 🌐 Multi-engine aggregation
- 📰 Multiple search categories
- 🎨 Rich formatted output
- 🚀 Fast JSON mode for programmatic use

## API

Uses your local SearXNG JSON API endpoint (no authentication required by default).