<?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>Llm-Security on Napat&#39;s Inverse Blog</title>
    <link>/tags/llm-security/</link>
    <description>Recent content in Llm-Security on Napat&#39;s Inverse Blog</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 02 Apr 2026 15:30:00 +0700</lastBuildDate>
    <atom:link href="/tags/llm-security/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Five OWASP AI Lists, One Practitioner Problem</title>
      <link>/2026-04-02-five-owasp-ai-lists-one-practitioner-problem/</link>
      <pubDate>Thu, 02 Apr 2026 15:30:00 +0700</pubDate>
      <guid>/2026-04-02-five-owasp-ai-lists-one-practitioner-problem/</guid>
      <description>&lt;p&gt;I was in a meeting recently where someone asked a simple question: &amp;ldquo;Which OWASP list should we use for our AI security review?&amp;rdquo;&lt;/p&gt;
&lt;p&gt;Nobody could answer it. Not because the people in the room were incompetent. The opposite, actually — they&amp;rsquo;d all read the lists, which is precisely why they couldn&amp;rsquo;t answer. There are five of them now. Five OWASP AI security lists. Each one a Top 10, except the one that&amp;rsquo;s a 200-page guide. They overlap, contradict, and occasionally talk past each other. When someone finally pulled up Matt Adams&amp;rsquo; &lt;a href=&#34;https://owaspai.matt-adams.co.uk/&#34;&gt;OWASP AI Top 10 Comparator&lt;/a&gt; — a tool that exists specifically because the proliferation problem is bad enough to need its own website — the room collectively sighed.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
