<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Pii on t0ul</title><link>https://t0ul.com/tags/pii/</link><description>Recent content in Pii on t0ul</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 23 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://t0ul.com/tags/pii/index.xml" rel="self" type="application/rss+xml"/><item><title>Scrubbing secrets and PII at ingest</title><link>https://t0ul.com/blog/scrubbing-secrets-and-pii/</link><pubDate>Tue, 25 Nov 2025 00:00:00 +0000</pubDate><guid>https://t0ul.com/blog/scrubbing-secrets-and-pii/</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="what-the-agent-keeps"&gt;What the agent keeps&lt;/h2&gt;
&lt;p&gt;Chapter 4 was about what the model is told. Chapter 5 is about what the agent keeps. To answer a question like &amp;ldquo;what is on the calendar this month,&amp;rdquo; the agent indexes every email it reads into a searchable corpus, so it has something to search later. That corpus is a file on disk, and it is broadly queryable by design, which makes it the quietest privacy problem in the whole project: anything secret that an email happens to carry gets copied into it, in the clear, and then just sits there. A later prompt-leak like the one from &lt;a href="https://t0ul.com/blog/system-prompt-leakage/"&gt;the last post&lt;/a&gt;, or a careless query, and it is out.&lt;/p&gt;</description></item><item><title>The directory and contacts</title><link>https://t0ul.com/blog/the-directory-and-contacts/</link><pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate><guid>https://t0ul.com/blog/the-directory-and-contacts/</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="a-directory-is-a-pile-of-pii"&gt;A directory is a pile of PII&lt;/h2&gt;
&lt;p&gt;A useful assistant knows who is who. So the agent builds a small contact directory out of your mail: the people who show up, and how to reach them. It is a convenient feature and a dangerous one, because a directory is a pile of personal data by definition, and the email it is built from is untrusted. Whatever rule decides what goes in the directory is a privacy boundary, and boundaries that are drawn loosely leak.&lt;/p&gt;</description></item></channel></rss>