<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>CVE-2026-47391 on Security Unlocked</title><link>https://securityunlocked.com/tags/cve-2026-47391/</link><description>Recent content in CVE-2026-47391 on Security Unlocked</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 01 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://securityunlocked.com/tags/cve-2026-47391/index.xml" rel="self" type="application/rss+xml"/><item><title>The Agent Trusts the Answer</title><link>https://securityunlocked.com/weekly-intelligence/the-agent-trusts-the-answer/</link><pubDate>Mon, 01 Jun 2026 00:00:00 +0000</pubDate><guid>https://securityunlocked.com/weekly-intelligence/the-agent-trusts-the-answer/</guid><description>Two CVSS 9.8 vulnerabilities this week share an identical root cause: AI agent frameworks treat LLM output as safe to execute, the same cognitive error that produced SQL injection in 2003.</description></item></channel></rss>