wechat-article-browseruse

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). This skill's fetch_wechat_article.py clearly opens and renders arbitrary public WeChat article URLs (mp.weixin.qq.com/s/...) via BrowserUse/Playwright and ingests the page DOM/text/images, and publish_wechat_article_to_feishu.py then uses that extracted, untrusted content (title/body) to create and publish Feishu docs—so public, user-generated web content is read and directly drives subsequent actions.