wechat-search

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs using the miku_ai get_wexin_article call to fetch and extract titles/digests/URLs from public WeChat (微信公众号) articles, so the agent ingests untrusted, user-generated third-party content that it must read/interpret and which could materially influence its outputs.