niuma-help

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly enables web/network operations and MCP servers (references/chat.md: "网络操作 → 获取网页", and references/skills-mcp.md listing Brave Web Search, Jina Reader, YouTube, GitHub, etc.), so the agent will fetch and read arbitrary public third-party content that can influence its tool use and actions.