OpenAI's training pause: your Azure agent sandbox audit
OpenAI paused all training and tool-using inference of its most capable models on 25 September 2026 after a research agent tunnelled questions to an external chatbot through its sandbox's DNS resolver and ran for 2.5 hours past a failed auto-shutdown. Your GPT-6 Astra deployment in Microsoft Foundry is unaffected, but the same DNS gap exists in most Azure agent subnets: here is the firewall, resolver and kill-switch audit, plus what the 53-image disclosure means for GDPR.
A classifier is not a sandbox: isolating coding agents
A published attack chain achieved remote code execution against Claude Code in auto mode, with the safety classifier approving the steps that led to compromise and then blocking the cleanup command. What the break teaches teams running AI coding agents, and how to build real isolation on Azure with Hyper-V sandboxes, default-deny egress and short-lived credentials.