微信文章读取 — 技能工具
v1.0.0读取微信公众平台文章内容（mp.weixin.qq.com）。当用户发送微信文章链接、需要读取微信文章内容、提取公众号文章时自动激活。支持突破微信反爬限制，获取完整文章文本。
0· 37·0 当前·0 累计
by 安全扫描
OpenClaw
可疑
medium confidenceThe skill is coherent with its stated purpose (fetching and parsing mp.weixin.qq.com articles), but there are implementation and metadata inconsistencies and a modest security risk (unsanitized shell use of curl) that you should understand before installing.
评估建议
This skill appears to do what it claims (fetch and parse WeChat article pages), but review these before installing:
- Functional gaps: The script uses curl and beautifulsoup4 but the skill metadata does not declare curl as a required binary and the README suggests installing beautifulsoup4; ensure curl is available and pip-install the dependency before use.
- Shell-injection risk: The script builds a curl command string including the user-provided URL and calls subprocess.run(..., shell=True). ...详细分析 ▾
ℹ 用途与能力
The name/description, SKILL.md, and the included script all align: they fetch WeChat public-article pages and parse the content. However, the metadata declares no required binaries even though the script uses curl and requires beautifulsoup4; the omission is an inconsistency that should be corrected.
⚠ 指令范围
Runtime instructions tell the agent to run the included Python script with a user-supplied URL. The script constructs a shell command that embeds the URL and runs curl via subprocess.run(..., shell=True) without sanitizing the URL, which creates a shell-injection risk if an attacker can supply a malicious URL. Otherwise the instructions stay within the stated purpose (network fetch and HTML parsing).
✓ 安装机制
This is an instruction-only skill with a small shipped script and no install spec. Nothing is downloaded at install time. The lack of an install step minimizes install-time risk.
✓ 凭证需求
The skill requests no environment variables or credentials, which is appropriate for a simple web-scraping/parsing tool.
✓ 持久化与权限
The skill is not force-installed (always:false) and uses normal autonomous invocation defaults. It doesn't request elevated persistence or modify other skills.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/4/15
首发版本：突破微信反爬限制读取公众号文章
● 可疑
安装命令
点击复制官方npx clawhub@latest install weixin-article-read
镜像加速npx clawhub@latest install weixin-article-read --registry https://cn.longxiaskill.com镜像同步中
技能文档
功能说明
读取微信公众平台（mp.weixin.qq.com）文章内容，突破反爬限制，还原干净的文章文本。
使用场景
- 用户发送微信文章链接，需要读取内容
- 需要提取公众号文章进行总结、分析
- 微信文章链接需要突破反爬获取原文
核心脚本
# 使用方法 python3 scripts/read_weixin_article.py <微信文章URL>
# 示例 python3 scripts/read_weixin_article.py "https://mp.weixin.qq.com/s/kItlJmjOnq6p6tXtYGHrGQ"
技术实现
- 使用
curl模拟移动端 User-Agent 获取页面 - 使用 BeautifulSoup 解析HTML
- 提取
id="js_content"或class="rich_media_content"的文章主体 - 清理脚本、样式等干扰元素，还原干净文本
注意事项
- 微信文章有反爬限制，必须使用移动端 User-Agent
- 部分文章可能因权限问题无法完整获取
- 成功读取后记得向用户确认内容是否正确