wechat-article-to-markdown

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and parses public WeChat article pages (mp.weixin.qq.com) — see SKILL.md workflow step 1 and scripts/wechat_article_pipeline.py (fetch_html, extract_article, image downloads and Markdown generation) — so it ingests untrusted third‑party content that is interpreted to produce outputs (and may trigger further formatting), enabling potential indirect prompt injection.