wechat-mp-scraper

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

• Third-party content exposure detected (high risk: 0.90). This skill automatically fetches and ingests public WeChat article pages (mp.weixin.qq.com) — see SKILL.md instructions to run scripts that call fetch_text/download_assets in scripts/scrape_wechat_mp.py and then read content.md, content.json, urls.json and snippets/ to drive explanations — so untrusted, user-generated third-party HTML is read and used to inform the agent's analysis and next actions.