<?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>OpenAI on Cybersecurity Blog</title><link>https://raphael-najee-monteiro.pages.dev/tags/openai/</link><description>Recent content in OpenAI on Cybersecurity Blog</description><generator>Hugo -- 0.147.7</generator><language>en-us</language><lastBuildDate>Sat, 04 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://raphael-najee-monteiro.pages.dev/tags/openai/index.xml" rel="self" type="application/rss+xml"/><item><title>This Week in AI Security: Agent Sandboxes Take a Beating</title><link>https://raphael-najee-monteiro.pages.dev/posts/2026-07-04-agent-sandboxes-under-fire/</link><pubDate>Sat, 04 Jul 2026 00:00:00 +0000</pubDate><guid>https://raphael-najee-monteiro.pages.dev/posts/2026-07-04-agent-sandboxes-under-fire/</guid><description>Two independent research teams broke the isolation layers agentic AI tools rely on this week, OpenAI previewed its most cyber-capable model yet under tight lockdown, and the UN put Big Tech CEOs in the same room as heads of state to govern it all.</description></item></channel></rss>