WeChat Article Fetcher

抓取微信公众号文章内容。当用户发送微信公众号文章链接（mp.weixin.qq.com）时自动触发，将文章内容提取为可读文本。无需API密钥。

Security Scan

The skill fetches WeChat article URLs by forwarding them to an undocumented third-party scraping API (down.mptext.top), which is coherent with the stated purpose but poses a privacy/exfiltration and trust risk that is not disclosed.

Purpose & Capability

The skill's stated purpose (fetch WeChat articles and convert to readable text) matches the SKILL.md instructions. However the instructions rely entirely on a third-party HTTP API (down.mptext.top) rather than fetching directly from the origin; that dependency is not declared in the metadata or description.

Instruction Scope

Runtime instructions tell the agent to URL-encode the user-provided mp.weixin.qq.com link and call https://down.mptext.top/api/public/v1/download?... . This directs entire user-supplied URLs (and therefore full article content or any URL-embedded tokens) to an external service, creating a clear data-exfiltration and privacy risk. The instructions also auto-trigger when a message contains an mp.weixin.qq.com link, so forwarding can happen without explicit user consent.

Install Mechanism

No install spec or code is present (instruction-only skill), so nothing is written to disk and there is no package-install risk.

Credentials

The skill requests no environment variables or credentials (proportionate). However, it implicitly requires network access to a third-party domain (down.mptext.top) which is not listed in metadata; that external dependency has privacy and trust implications even though no secrets are requested.

Persistence & Privilege

always is false, the skill is user-invocable and can be invoked autonomously (default). It does not request persistent privileges or modify system/agent configuration.

What to consider before installing

This skill will forward any WeChat article URL a user provides to a third-party scraper at down.mptext.top and return the scraped text. Before installing, consider: (1) Privacy: the external service will receive the full URL and the scraped content — this may expose private articles or URL tokens. (2) Trust: the service's ownership and data-handling practices are unknown (no homepage/source). (3) Availability and correctness: scraped content, images, and formatting may be unreliable. If you need this capability, prefer a transparent alternative: host your own scraper, require explicit user consent before sending links, or ask the skill author for source code and a privacy policy. Avoid using the skill for sensitive or private links until you can verify the third-party service's trustworthiness.

微信公众号文章抓取

触发条件

用户消息中包含 mp.weixin.qq.com 链接时，自动使用此技能抓取文章内容。

使用方法

curl -s "https://down.mptext.top/api/public/v1/download?url=<URL_ENCODED_LINK>&format=markdown"

参数

参数	说明
url	文章链接（需URL编码）
format	输出格式：html / markdown / text / json（默认html）

步骤

1. 从用户消息中提取微信文章链接
2. 对链接进行 URL 编码
3. 调用接口抓取内容（推荐 markdown 格式）
4. 提取正文，去除 CSS、导航等噪音
5. 为用户生成文章摘要或回答用户关于文章的问题

注意事项

• 此接口无需 API 密钥
• 部分文章可能有字数限制或反爬处理
• 图片链接可能有时效性
• 如抓取失败，可尝试换 format 为 text