niuma-help

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly enables the agent to fetch and read public third‑party content (see "获取网页" / "网络搜索" in references/chat.md) and to auto‑call built‑in MCP servers such as Brave Web Search and Jina Reader (references/skills-mcp.md), so untrusted web content can be read and can materially influence the agent's automatic tool use and task execution.