<?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>Prompt Injection on secderr</title><link>https://secderr.tech/tags/prompt-injection/</link><description>Recent content in Prompt Injection on secderr</description><image><title>secderr</title><url>https://secderr.tech/images/og-default.png</url><link>https://secderr.tech/images/og-default.png</link></image><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 09 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://secderr.tech/tags/prompt-injection/index.xml" rel="self" type="application/rss+xml"/><item><title>Read-Only and Logged: Security Requirements for AI Agents on Your Admin Platforms</title><link>https://secderr.tech/posts/ai-agents-read-only-and-logged/</link><pubDate>Mon, 09 Nov 2026 00:00:00 +0000</pubDate><guid>https://secderr.tech/posts/ai-agents-read-only-and-logged/</guid><description>An AI agent is a new privileged user that reads untrusted text. Two requirements make it safe to ship: read-only access and a log of every call.</description></item></channel></rss>