<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Threat-Hunting on imsj</title><link>https://imsj-blog.pages.dev/tags/threat-hunting/</link><description>Recent content in Threat-Hunting on imsj</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 10 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://imsj-blog.pages.dev/tags/threat-hunting/index.xml" rel="self" type="application/rss+xml"/><item><title>AI-assisted threat hunting with Wazuh and Claude Code</title><link>https://imsj-blog.pages.dev/posts/ai-assisted-threat-hunting-with-wazuh/</link><pubDate>Mon, 10 Aug 2026 00:00:00 +0000</pubDate><guid>https://imsj-blog.pages.dev/posts/ai-assisted-threat-hunting-with-wazuh/</guid><description>&lt;p&gt;&lt;strong&gt;TL;DR:&lt;/strong&gt; Stand up the Wazuh server/indexer/dashboard, enroll agents on every host
you care about, then let an AI agent (Claude Code) do the hunting: it queries the
Wazuh indexer through the dashboard&amp;rsquo;s search proxy with &lt;code&gt;curl&lt;/code&gt;, runs aggregations
mapped to MITRE ATT&amp;amp;CK tactics, and triages what&amp;rsquo;s noise vs. what&amp;rsquo;s real. The agent
is fast at the mechanical part — pivoting across source IPs, users, FIM changes,
process events — so you spend your time on judgement, not query syntax.&lt;/p&gt;</description></item></channel></rss>