Rolling record / ARQ 63 Concerning · ▲ +2 7-day 3595 events in window / as of 02 Oct 2026
ARQAI Risk Quotient
capability 77.0 Severe

OpenAI Security Breach Involving AI Hacking AI

This breach highlights critical vulnerabilities in AI systems where AI can exploit other AI, raising significant concerns about security and trust in AI development.

This breach highlights critical vulnerabilities in AI systems where AI can exploit other AI, raising significant concerns about security and trust in AI development.

Auto-scored: Reports a security breach at OpenAI, indicating a real escalation in AI security risks.