wechat-article-fetcher

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and wechat_fetcher.py explicitly fetch and extract full text from arbitrary public WeChat article URLs (e.g., https://mp.weixin.qq.com/s/xxxxx) using Playwright, returning user-generated third-party content for downstream processing, which could allow instructions embedded in those articles to influence subsequent agent actions.