Rolling record / ARQ 63 Concerning · ▲ +2 7-day 3595 events in window / as of 02 Oct 2026
ARQAI Risk Quotient
capability 68.1 Concerning

AI-Built Exploit and Sign-In Flaw Breached OpenAI Internal Code

This event highlights the use of AI to create security exploits, posing real risks to system integrity and escalating capability misuse.

This event highlights the use of AI to create security exploits, posing real risks to system integrity and escalating capability misuse.

Auto-scored: Security breach involving AI exploit represents a real escalation in capability jump.