<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>RelentLens Blog</title><description>Continuous threat modeling and AI-agent security, from Vantaura Security.</description><link>https://vantaurasecurity.com/</link><item><title>Your Threat Model Was Obsolete Before You Finished Drawing It</title><link>https://vantaurasecurity.com/blog/your-threat-model-was-obsolete/</link><guid isPermaLink="true">https://vantaurasecurity.com/blog/your-threat-model-was-obsolete/</guid><description>Classic threat modeling assumes a system that holds still. Autonomous agents don&apos;t — and the July 2026 Hugging Face incident shows why design-time and runtime have to be one continuous picture.</description><pubDate>Thu, 03 Sep 2026 00:00:00 GMT</pubDate></item></channel></rss>