<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Permissions on CodeBerry</title>
    <link>https://codeberry.work/tags/permissions/</link>
    <description>Recent content in Permissions on CodeBerry</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>ko</language>
    <copyright>© 2026 성경재</copyright>
    <lastBuildDate>Fri, 08 May 2026 14:30:00 +0900</lastBuildDate><atom:link href="https://codeberry.work/tags/permissions/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>Anthropic 엔지니어링 블로그 #22: Claude Code Auto Mode — 권한 팝업과 &#39;위험한 다 허용&#39; 사이의 중간</title>
      <link>https://codeberry.work/ai-news/claude-code-auto-mode/</link>
      <pubDate>Fri, 08 May 2026 14:30:00 +0900</pubDate>
      
      <guid>https://codeberry.work/ai-news/claude-code-auto-mode/</guid>
      <description>사용자가 권한 팝업의 93%를 그냥 승인한다. 그렇다고 다 허용은 위험하다. 분류기가 위험 행동만 골라 차단하는 Auto Mode가 그 중간을 채운다.</description>
      
    </item>
    
  </channel>
</rss>
