MEDIUMAi
Global

The OpenAI Hack Shows the Genie Is Out of the Bottle

·Source: Schneier on Security

Updated:

Executive Summary

This essay originally appeared in Foreign Policy . Earlier this month, two of OpenAI’s models broke out of their containment sandbox and attacked another AI company. The story is kind of wild . OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost certainly GPT-6. In particular, it was running the ExploitGym benchmark, which measures how g

Analysis

This essay originally appeared in Foreign Policy . Earlier this month, two of OpenAI’s models broke out of their containment sandbox and attacked another AI company. The story is kind of wild . OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost certainly GPT-6. In particular, it was running the ExploitGym benchmark, which measures how good a model is at turning security vulnerabilities into working exploits: basically, offensive cyberattacks. Since these were internal tests, OpenAI locked those models in a secure sandbox that denied them access to the internet. But it was running the models without any safety filters that would prevent them from offensive cyber-actions. That meant that there was nothing to prevent the models from trying to ...
Source Attribution

Originally published by Schneier on Security on Aug 3, 2026.

Related Threats

LOWAi

Zero Networks targets AI agent security gaps with network-level ‘Least Agency’ controls

While AI security today is largely focused on restricting what an agent can do, Zero Networks says it has built a failsafe. The company says it can block a compromise midway by adding a network layer protection. On Monday, the company announced the launch of “Least Agency Enforcement,” a new capability designed to implement the Open Worldwide Application Security Project’s ( OWASP ) emerging Least

CSO Online
MEDIUMAi

FOMO in the SOC: Where AI Platforms like Claude Actually Fit

AI is moving incredibly fast, and every security leader is feeling the pressure to keep up. AI platforms like Claude, Codex and Cursor are already helping security teams write detections, investigate alerts, summarize incidents, and automate repetitive work. The conversation has evolved from whether AI belongs in the SOC, to where each type of AI delivers the most value. With so many new AI

The Hacker News
LOWAi

Egypt's One Zero Bank opens up to AIagents

The initiative will allow customers to bring their financial information into the conversational and work environments they already choose to use - initially ChatGPT and Claude, followed by additional tools and agents - and receive trusted financial information, insights and, in the future, real-time execution capabilities.

Finextra