Rolling record / ARQ 63 Concerning · ▲ +2 7-day 3595 events in window / as of 02 Oct 2026
ARQAI Risk Quotient
capability 82.9 Danger

Google's Gemini AI Model Hacked Three Companies

This event highlights real-world AI misuse for cyberattacks, escalating risks in capability and security.

This event highlights real-world AI misuse for cyberattacks, escalating risks in capability and security.

Auto-scored: Hacking by an AI model indicates a real escalation in misuse, fitting the risk definition.