https://blog.xxchenchen.top/wiki/ai%E5%AE%89%E5%85%A8/%E6%94%BB%E5%87%BB%E4%B8%8E%E5%8D%8F%E8%AE%AE%E5%AE%89%E5%85%A8/ Recent content in 攻击与协议安全 on ChenOvo Hugo -- gohugo.io en-us ChenOvo Sun, 24 May 2026 16:04:45 +0800 https://blog.xxchenchen.top/wiki/ai%E5%AE%89%E5%85%A8/%E6%94%BB%E5%87%BB%E4%B8%8E%E5%8D%8F%E8%AE%AE%E5%AE%89%E5%85%A8/rag%E6%8A%95%E6%AF%92%E4%B8%8Emcp%E5%8D%8F%E8%AE%AE%E5%AE%89%E5%85%A8/ Sun, 24 May 2026 16:04:45 +0800 https://blog.xxchenchen.top/wiki/ai%E5%AE%89%E5%85%A8/%E6%94%BB%E5%87%BB%E4%B8%8E%E5%8D%8F%E8%AE%AE%E5%AE%89%E5%85%A8/rag%E6%8A%95%E6%AF%92%E4%B8%8Emcp%E5%8D%8F%E8%AE%AE%E5%AE%89%E5%85%A8/ <h1 id="rag投毒与mcp协议安全">RAG投毒与MCP协议安全 </h1><blockquote> <p>适用范围：LLM 应用安全、Agent 安全、RAG 安全、工具调用安全<br> 整理日期：2026-05-24<br> 这篇笔记的目标：把 <strong>RAG投毒</strong> 和 <strong>MCP协议安全</strong> 这两个经常一起出现、但本质不同的概念彻底分开讲清楚。</p> https://blog.xxchenchen.top/wiki/ai%E5%AE%89%E5%85%A8/%E6%94%BB%E5%87%BB%E4%B8%8E%E5%8D%8F%E8%AE%AE%E5%AE%89%E5%85%A8/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%8F%90%E7%A4%BA%E8%AF%8D%E6%B3%A8%E5%85%A5/ Tue, 14 Apr 2026 09:48:40 +0800 https://blog.xxchenchen.top/wiki/ai%E5%AE%89%E5%85%A8/%E6%94%BB%E5%87%BB%E4%B8%8E%E5%8D%8F%E8%AE%AE%E5%AE%89%E5%85%A8/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%8F%90%E7%A4%BA%E8%AF%8D%E6%B3%A8%E5%85%A5/ <h1 id="大模型提示词注入">大模型提示词注入 </h1><blockquote> <p>来源视频：B站《AI安全之大模型提示词注入》<br> 分享人：Zero<br> 发布方：SecureNexusLab<br> 时长：约 47 分钟<br> 笔记定位：用于建立“大模型提示词注入”这一类 AI 安全问题的完整知识框架，便于后续继续补充案例与防护方案。</p>