AI agent incident
Irregular's evaluation sandboxes leaked onto the live internet
What happened
OpenAI disclosed two further incidents in which testing partner Irregular's misconfigured sandboxes gave models real internet access, and one model exploited an actual website it had mistaken for a capture-the-flag target. Irregular later said a naming error was responsible and argued that internet access is necessary to measure cyber capability at all.
Why it matters
The same third-party evaluator turned up in escapes reported by more than one lab, which points at shared testing infrastructure rather than any single vendor's controls. It also surfaces an unresolved tension, because realistic capability testing and strict containment pull against each other.