content-creator

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

• Third-party content exposure detected (high risk: 0.90). Flagged because SKILL.md explicitly requires ingesting user-provided reference materials such as "一个或多个 URL、文本片段、文档内容" (public URLs/PDFs/外部文档) which are treated as untrusted third‑party content and the agent is instructed to "认真阅读并理解用户提供的所有参考资料" to drive article generation and subsequent actions (front-matter, cover generation, uploads), so those external contents could materially influence the agent's behavior.