wechat-10w-hot

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads a WeChat article database JSON file (temp_articles.json) produced by fetch_hot_articles.py, which aggregates articles from third-party public WeChat Official Accounts containing unconstrained outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The script scripts/fetch_hot_articles.py fetches data from an external API https://redfox.hk/story/api/cozeSkill/getWxDataByCategoryAndTime, creating a common/reputable unofficial operational dependency.