<?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>防泄露 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E9%98%B2%E6%B3%84%E9%9C%B2/</link><description>Recent content in 防泄露 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>Tue, 30 Jun 2026 11:15:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E9%98%B2%E6%B3%84%E9%9C%B2/index.xml" rel="self" type="application/rss+xml"/><item><title>Prompt安全加固：防注入、防泄露、防操纵</title><link>https://guijiagi.com/posts/prompt-security-hardening-injection-leak-manipulation/</link><pubDate>Tue, 30 Jun 2026 11:15:00 +0800</pubDate><guid>https://guijiagi.com/posts/prompt-security-hardening-injection-leak-manipulation/</guid><description>系统介绍Prompt安全加固的完整方案，覆盖防注入、防System Prompt泄露、防用户操纵三大核心领域，提供工程化实现</description></item></channel></rss>