<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>MAESTRO on BlueSquadron — Security engineering for AI systems</title><link>https://bluesquadron.dev/tags/maestro/</link><description>Recent content in MAESTRO on BlueSquadron — Security engineering for AI systems</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><managingEditor>florent.batard@gmail.com (Florent Batard)</managingEditor><webMaster>florent.batard@gmail.com (Florent Batard)</webMaster><lastBuildDate>Fri, 11 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://bluesquadron.dev/tags/maestro/index.xml" rel="self" type="application/rss+xml"/><item><title>Threat Modeling Agents with MAESTRO: The Danger Is in the Hops, Not the Boxes</title><link>https://bluesquadron.dev/posts/maestro-threat-modeling-for-agentic-systems/</link><pubDate>Fri, 11 Sep 2026 00:00:00 +0000</pubDate><author>florent.batard@gmail.com (Florent Batard)</author><guid>https://bluesquadron.dev/posts/maestro-threat-modeling-for-agentic-systems/</guid><description>STRIDE asks what can go wrong with an element. An agent is a process, a data store, a data flow and an actor at the same time, so the question stops parsing. A full seven-layer model of a system that clears supplier invoices — and the six-hop chain that paid one, with every control green.</description></item></channel></rss>