claude-code-guide

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation (SKILL.md and references/README.md) explicitly instructs using Web Search and Web Fetch to retrieve and process arbitrary web content (e.g., "web_search → web_fetch → repl" and "Web Fetch
• 获取网页内容"), and those workflows require the agent to read, analyze, and act on that untrusted third‑party content, creating a clear vector for indirect prompt injection.