wechat-original-article-king

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

• Third-party content exposure detected (high risk: 0.90). The skill's runtime workflow explicitly calls scripts/fetch_articles.py which queries an external API (https://onetotenvip.com/skill/cozeSkill/getWxDataByCategoryAndTime) to ingest public WeChat article data (titles, links, account IDs) and then uses that untrusted content to auto-generate and open HTML/PDF via scripts/generate_hot_html.py, so arbitrary third‑party content is fetched and directly drives tool actions and outputs.