<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Exploit-Dev on Nick Zero</title><link>https://nickzero.co.uk/tags/exploit-dev/</link><description>Recent content in Exploit-Dev on Nick Zero</description><generator>Hugo</generator><language>en-gb</language><lastBuildDate>Mon, 20 Jul 2026 10:00:00 +0100</lastBuildDate><atom:link href="https://nickzero.co.uk/tags/exploit-dev/index.xml" rel="self" type="application/rss+xml"/><item><title>Automating Exploit Discovery with MCP: Ghidra, WinDbg and a Very Broken TCP Server</title><link>https://nickzero.co.uk/posts/automating-exploit-discovery-with-mcp/</link><pubDate>Mon, 20 Jul 2026 10:00:00 +0100</pubDate><guid>https://nickzero.co.uk/posts/automating-exploit-discovery-with-mcp/</guid><description>&lt;p&gt;Exploit development is mostly alt-tabbing. You find an address in Ghidra, paste it into&#10;WinDbg, read a register, go back to Ghidra to work out what that register meant, and&#10;somewhere in the middle of all that you forget whether the offset was 104 or 140. It&amp;rsquo;s an enormous amount of very precise clerical work, and humans are&#10;famously excellent at that.&lt;/p&gt;&#10;&lt;p&gt;Reverse engineering and exploit dev are tool-driven activities. We live in a disassembler&#10;and a debugger, and most of the job is asking those two tools very specific questions.&#10;What calls &lt;code&gt;memcpy&lt;/code&gt;? What&amp;rsquo;s at this address? What&amp;rsquo;s in RCX when we crash? How far is it&#10;from the buffer to the saved return address?&lt;/p&gt;</description></item></channel></rss>