content-checker

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires ingesting "原始参考资料（必须）" such as URLs, PDFs or source documents and directs the agent to "仔细阅读“原始参考资料”" and fetch webpage content (see the "接收信息" and "获取网页内容方式限制" sections of SKILL.md), which means it reads untrusted third‑party web content that can influence fact‑checking decisions and thus could enable indirect prompt injection.