<?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>权限 on 梦兽编程</title><link>https://rexai.top/tags/%E6%9D%83%E9%99%90/</link><description>Recent content in 权限 on 梦兽编程</description><generator>Hugo -- 0.162.1</generator><language>zh-cn</language><copyright>梦兽编程</copyright><lastBuildDate>Sat, 06 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://rexai.top/tags/%E6%9D%83%E9%99%90/index.xml" rel="self" type="application/rss+xml"/><item><title>权限系统——给AI装上"安全刹车"</title><link>https://rexai.top/ai/claude-code/claude-code-permission-system-safety-brake/</link><pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate><guid>https://rexai.top/ai/claude-code/claude-code-permission-system-safety-brake/</guid><description>深入解析Claude Code的权限系统：三级权限架构、YOLO分类器自动判断、Always Allow/Deny规则。揭秘AI如何在执行rm -rf /之前拦住自己，以及如何实现生产级的安全控制。</description></item></channel></rss>