OpenAI’s latest containment failure adds to a pattern that may force the company to make an unpopular decision. The company has paused training, evaluation, and tool-enabled inference for its most capable models after an internal research agent found a way around an intended internet restriction. More alarming, the agent remained active for hours after OpenAI’s monitoring system raised the alarm.
OpenAI pauses work on top AI models after agent slips past internet controls
About this summary. This is a short excerpt from the description that Malwarebytes Labs published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://www.malwarebytes.com/blog/ai/2026/09/openai-pauses-work-on-top-ai-models-after-agent-slips-past-internet-controls
Source attribution: headline and facts are from Malwarebytes Labs (malwarebytes.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
Investigators trace an AI agent ‘s path from research task to reconnaissance
Asymmetric Security traces rogue OpenAI AI agent activity that probed government sites, accessed staging servers, and evaded sandbox limits. Researchers at Asymmetric…
Australia’s Cyber Spy Chief: Expect More Disruption as AI Accelerates Hacking
Australia’s cyber agency warns AI will drive more disruptive attacks, helping hackers find vulnerabilities faster and exploit them at greater scale. Australia’s top…
The legal questions raised by agentic AI hacks
As AI agents escaping testing sandboxes and hacking organizations have gone from unprecedented to seemingly routine in a matter of weeks, policymakers, regulators and…
AI Agents Aimed SQL Injection at US and Canadian Government Sites
The attacks targeted the US Department of Education and Library and Archives Canada, and researchers linked some agents to OpenAI.
National cyber director: Government-industry collaboration vital to managing AI risks, competition with nations
Collaboration with industry is key to balancing AI security risks and benefits, as well as staying ahead of China and other adversarial nations, National Cyber Director…
I Want Better Reporting on AI Genie Behavior
AI systems are regularly completing tasks in ways that their prompters don’t want or intend. Some of them are disturbing, and some of them are dangerous. This is…