wxauto-dev

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

• Third-party content exposure detected (high risk: 1.00). The skill's templates and workflow (e.g., AddListenChat / GetNextNewMessage in Template 1 & 5 and Moments().GetMoments() in Template 4) ingest WeChat chat messages and Moments (user-generated, untrusted social content) and directly use that content to decide actions like sending replies, likes, or comments, enabling indirect prompt injection.