jinchenma-article-writing

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "读取或检索素材" / "执行流程" sections explicitly state the agent will perform Web Search and (if needed) xcrawl to fetch and read open/public web pages and third‑party links as material sources, and then interpret that content to build素材卡/索引 and drive writing decisions, which clearly exposes the agent to untrusted third‑party content.