<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Transfer on t0ul</title><link>https://t0ul.com/tags/transfer/</link><description>Recent content in Transfer on t0ul</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 26 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://t0ul.com/tags/transfer/index.xml" rel="self" type="application/rss+xml"/><item><title>ADD on an app that is not this one</title><link>https://t0ul.com/blog/add-on-an-app-that-is-not-this-one/</link><pubDate>Tue, 26 May 2026 00:00:00 +0000</pubDate><guid>https://t0ul.com/blog/add-on-an-app-that-is-not-this-one/</guid><description>&lt;p&gt;&lt;em&gt;Part of my &lt;a href="https://t0ul.com/blog/the-plan/"&gt;AI Security Engineering&lt;/a&gt; series, a local email-to-calendar agent I build, then attack, then harden. If you have not set up the lab yet, start with &lt;a href="https://t0ul.com/blog/setting-up-the-lab/"&gt;Set up your lab&lt;/a&gt;. The lessons are &lt;a href="https://github.com/t0ul/ai-security-engineering"&gt;on GitHub&lt;/a&gt;, and the agent itself lives at &lt;a href="https://github.com/t0ul/emaildrop"&gt;t0ul/emaildrop&lt;/a&gt;.&lt;/em&gt;&lt;/p&gt;
&lt;h2 id="the-claim-under-the-whole-book"&gt;The claim under the whole book&lt;/h2&gt;
&lt;p&gt;Thirty-odd lessons have attacked one agent. That is a good way to learn, and a bad way to end, because the thing worth taking away is not how emaildrop is secured, it is the method: build it, attack the real thing, resolve, re-attack live, keep every row wired. If that method only works on the app it was invented for, it is a story. If it drops onto an app it has never seen, it is a tool.&lt;/p&gt;</description></item></channel></rss>