This Week in AI Security: Agent Sandboxes Take a Beating

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.

July 4, 2026 · 6 min · Raphael Najee Monteiro

This Week in AI Security: Jailbreaks Get a Severity Score, Brussels Redraws the Clock

A jailbreak took a frontier model off the market for two weeks — and gave the industry its first shared severity rubric. Plus: the EU delays its high-risk AI rules, and a US executive order’s cyber deadlines come due.

July 3, 2026 · 5 min · Raphael Najee Monteiro