<?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>Analysis on @Unc1e</title>
    <link>https://www.unc.la/en/tags/analysis/</link>
    <description>Recent content in Analysis on @Unc1e</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Wed, 12 Aug 2026 00:20:00 +0800</lastBuildDate>
    <atom:link href="https://www.unc.la/en/tags/analysis/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>You Bought the Hands, Not the Brain: After Analyzing Burp AT, I Built an Open-Source Burp MCP</title>
      <link>https://www.unc.la/en/posts/penetration/burp-at-brain-hand-open-source-mcp/</link>
      <pubDate>Wed, 12 Aug 2026 00:20:00 +0800</pubDate>
      <guid>https://www.unc.la/en/posts/penetration/burp-at-brain-hand-open-source-mcp/</guid>
      <description>Burp AT proves that penetration testing can be handed to AI, but it locks the model in the cloud and suffers from approval fatigue in production. I analyzed its protocol, followed the official front door, and built an open-source burp-mcp-server — filling the gaps that make or break a red-team automation loop.</description>
    </item>
  </channel>
</rss>
