feishu-doc-converter

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests public, user-generated web content (see SKILL.md and the url_to_md() workflow) — for example _wechat_to_md() imports wechat-article-fetcher to fetch mp.weixin.qq.com articles and _doc_to_md_by_browser()/SKILL.md instruct using browser.open() for external Feishu/wiki URLs — so the agent will read untrusted third-party pages as part of its runtime conversion flow.