claude-code-guide

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly includes Web Search and Web Fetch tools and examples (e.g., "Web Fetch
• 获取网页内容", "HTML 转 Markdown", and the example "使用 web_fetch 获取 https://api.example.com/data") and links to public GitHub repos, which show the agent fetching and reading arbitrary public web content that could be untrusted user-generated material.