devdocs-insights

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly supports "从 URL 提取建议" and shows an example where the agent performs "[WebFetch 获取内容]" on a public article (e.g., https://example.com/react-patterns) and then analyzes that fetched content to generate actionable recommendations, so it ingests and acts on untrusted third‑party web content.