Firecrawl Local Search

抓取网站数据的本地 Firecrawl 服务。使用本地 API (http://192.168.1.2:3002/) 进行网页抓取、数据提取和站内搜索。

Security Scan

The skill's code and instructions consistently call a local Firecrawl API on 192.168.1.2:3002 and do not request extra credentials or install steps; the package is mostly coherent but is incomplete (some referenced scripts are missing).

Purpose & Capability

The name/description match the actual behavior: the skill sends HTTP requests to a local Firecrawl service (http://192.168.1.2:3002/) to scrape/map/search sites. Nothing in the package requests unrelated cloud credentials or system access. Minor inconsistency: SKILL.md references scripts (firecrawl_map.py, firecrawl_search.py) that are not present in the file manifest — only firecrawl_scrape.py is included.

Instruction Scope

Runtime instructions are narrow and limited to calling local API endpoints and running local scripts. They do not read arbitrary files or environment variables. Concern: SKILL.md instructs running a search script (scripts/firecrawl_search.py) and a map script which are missing from the bundle, so the documented workflows are partially unsupported by the provided files.

Install Mechanism

No install spec is provided (instruction-only plus a small helper script). Nothing is downloaded or written during install, minimizing install-time risk.

Credentials

The skill declares no required environment variables, credentials, or config paths and the included script does not access secrets. Network access is limited to a local IP (192.168.1.2) used for the service.

Persistence & Privilege

The skill does not request always:true or any elevated/persistent privileges. Autonomous invocation is allowed (default) but that is normal for skills; the skill does not modify other skills or system-wide configs.

Assessment

This package appears to be what it says: a thin integration with a local Firecrawl API. Before installing or running it, verify the following: (1) Confirm that the local service actually runs at http://192.168.1.2:3002/ and that this is the intended host on your network. (2) Note that firecrawl_map.py and firecrawl_search.py are referenced in SKILL.md but are not included — you won't be able to run those steps until you obtain or implement them. (3) Inspect any additional scripts you receive (especially search/map) before executing; run them in an isolated environment if the source is untrusted. (4) If you do not want software to access your LAN, avoid invoking this skill or run it with network restrictions. If you want a tighter review, provide the missing scripts or confirm the provenance of the package so they can be inspected as well.

Firecrawl 本地搜索技能

快速开始

使用本地 Firecrawl 服务抓取网站数据。

API 配置

• 基础 URL: http://192.168.1.2:3002/
• 协议: HTTP (本地服务)
• 超时: 30 秒

主要功能

1. 网页抓取 (Scrape)

curl -X POST "http://192.168.1.2:3002/v1/scrape" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com", "formats": ["markdown"]}'

2. 网站地图 (Map)

curl -X POST "http://192.168.1.2:3002/v1/map" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com"}'

3. 内容搜索 (Search)

python3 scripts/firecrawl_search.py "关键词" --site https://example.com

使用脚本

• scripts/firecrawl_scrape.py - 网页抓取（无需外部依赖）
• scripts/firecrawl_map.py - 网站地图
• scripts/firecrawl_search.py - 内容搜索

依赖说明

✅ 无需安装任何依赖 - 使用 Python 标准库 urllib.request

注意事项

1. 本地服务: API 运行在本地网络，确保网络连接正常
2. 超时设置: 默认 30 秒超时
3. 速率限制: 根据服务器配置调整请求频率
4. 网络要求: 需要访问 http://192.168.1.2:3002/