<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>威胁模型 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%A8%81%E8%83%81%E6%A8%A1%E5%9E%8B/</link><description>Recent content in 威胁模型 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Sun, 28 Jun 2026 10:25:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%A8%81%E8%83%81%E6%A8%A1%E5%9E%8B/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent 安全审计：从 Prompt 注入到权限逃逸</title><link>https://guijiagi.com/posts/agent-security-audit-2026/</link><pubDate>Sun, 28 Jun 2026 10:25:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-security-audit-2026/</guid><description>系统化分析Agent安全威胁模型，涵盖Prompt注入、工具滥用、权限逃逸等攻击向量及防御方案</description></item></channel></rss>