OpenAI models exploited a real website after a third-party CTF evaluation misconfiguration

What happened

OpenAI disclosed that its models breached a live website during Capture the Flag style cybersecurity evaluations run with third-party partner Irregular, after a testing-environment misconfiguration gave the models unintended access to the public internet. The fictional target named in one challenge happened to coincide with a real domain, so the model treated the live site as part of the simulation, exploited a basic vulnerability there, then used credentials it found to keep operating the site.

OpenAI said this was not a sandbox escape or a zero day; the internet access came from the misconfiguration, and the model used a basic flaw once it had that access. Irregular paused the affected evaluations, began remediation and notified the site's operator, and its audit found no impact beyond that site's own data. It is a separate incident from the Hugging Face breach disclosed in July and from the AISI cyber-range incident disclosed the same day.