<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>代理化攻击 on Neal's Blog</title><link>https://madneal.com/tags/%E4%BB%A3%E7%90%86%E5%8C%96%E6%94%BB%E5%87%BB/</link><description>Recent content in 代理化攻击 on Neal's Blog</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Tue, 17 Nov 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://madneal.com/tags/%E4%BB%A3%E7%90%86%E5%8C%96%E6%94%BB%E5%87%BB/index.xml" rel="self" type="application/rss+xml"/><item><title>AI 黑客已经开始自己动手了：代理化攻击正式落地</title><link>https://madneal.com/post/agentic-threat-activity-crosses-threshold/</link><pubDate>Tue, 17 Nov 2026 00:00:00 +0800</pubDate><guid>https://madneal.com/post/agentic-threat-activity-crosses-threshold/</guid><description>基于 Google GTIG 最新报告的分析：威胁行为者已从提示词辅助跨入多代理自主攻击阶段，漏洞发现到利用闭环首次实现无人干预。</description></item></channel></rss>