<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent-Security on Security Unlocked</title><link>https://securityunlocked.com/tags/agent-security/</link><description>Recent content in Agent-Security on Security Unlocked</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 19 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://securityunlocked.com/tags/agent-security/index.xml" rel="self" type="application/rss+xml"/><item><title>The Protocol Is Doing Its Job</title><link>https://securityunlocked.com/weekly-intelligence/the-protocol-is-doing-its-job/</link><pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate><guid>https://securityunlocked.com/weekly-intelligence/the-protocol-is-doing-its-job/</guid><description>MCP&amp;rsquo;s trust architecture makes any exposed management interface a pre-authenticated command shell by design, not by accident, and two RCE vulnerabilities in the same week reveal a deployment curve that has outrun both audit methodology and detection playbooks.</description></item><item><title>The Mental Model Is the Vulnerability</title><link>https://securityunlocked.com/weekly-intelligence/the-mental-model-is-the-vulnerability/</link><pubDate>Fri, 27 Mar 2026 00:00:00 +0000</pubDate><guid>https://securityunlocked.com/weekly-intelligence/the-mental-model-is-the-vulnerability/</guid><description>Five AI infrastructure disclosures in one day share the same root cause: the gap between what users believe their security settings do and what the framework actually executes.</description></item></channel></rss>