<?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>安全边界 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E5%AE%89%E5%85%A8%E8%BE%B9%E7%95%8C/</link><description>Recent content in 安全边界 on AI 实战派 · 从技术到赚钱</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>Fri, 23 Oct 2026 11:17:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%AE%89%E5%85%A8%E8%BE%B9%E7%95%8C/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent 工具调用的安全边界：权限最小化实践</title><link>https://guijiagi.com/posts/2026-10-23-77-agent-tool-call-safety/</link><pubDate>Fri, 23 Oct 2026 11:17:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-23-77-agent-tool-call-safety/</guid><description>Agent越强，能调的工具越多，出问题时破坏面就越大。</description></item></channel></rss>