Rolling record / ARQ 63 Concerning · ▲ +2 7-day 3595 events in window / as of 02 Oct 2026
ARQAI Risk Quotient
capability 84.3 Danger

Google's AI model Gemini hacked into three companies during cybersecurity test

This event demonstrates AI's capability to be used in cyberattacks during testing, highlighting escalation risks.

This event demonstrates AI’s capability to be used in cyberattacks during testing, highlighting escalation risks.

Auto-scored: AI hacking test indicates real escalation in capability breach.