wechat-product-manager-writer

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to perform WebSearch and use WebFetch to retrieve and extract content from open/public third-party sites (e.g., 知乎, 即刻, 产品媒体 and arbitrary product/blog pages) and to read/interpret that user-generated/untrusted content as part of the article-writing workflow.