Wechat Look

读取微信公众号文章的专用工具，支持OCR文字识别。自动规范化URL并提取文章内容，识别图片中的中英文文字。

This skill appears coherent for reading WeChat articles and performing OCR, but before installing consider: (1) It will fetch article HTML and download every image referenced in the page — those image URLs are external and may reveal that you requested that page (privacy/fingerprinting). (2) The Node layer requires running 'npm install' which will install tesseract.js and other npm packages; npm packages can execute install scripts, so inspect package.json/package-lock and prefer installing in an isolated environment (container or sandbox) if you are cautious. (3) tesseract.js may attempt to fetch language model / WASM assets at runtime depending on configuration; this implies additional network access beyond image downloads. (4) The skill spawns local Node processes (subprocess) to perform OCR; confirm your environment policy allows executing the bundled scripts. If these behaviors are acceptable, the skill's footprint is proportionate to its purpose. If you need to limit exposure, run it in an isolated runtime, review the node modules, or modify the OCR scripts to use pre-downloaded language models.

Type: OpenClaw Skill Name: wechat-look Version: 1.0.1 The skill bundle provides a legitimate utility for reading WeChat articles and performing OCR on embedded images using a Python and Node.js hybrid architecture. It uses subprocess.run safely to invoke Node.js scripts (ocr_chinese.js, ocr.js) and utilizes standard libraries like tesseract.js and requests for its core functionality. While the tool fetches external content and processes image URLs from the web, its behavior is consistent with the stated purpose, and no evidence of malicious intent, data exfiltration, or prompt injection was found.