Rolling record / ARQ 63 Concerning · ▲ +2 7-day 3595 events in window / as of 02 Oct 2026
ARQAI Risk Quotient
capability 68.7 Concerning

Google's Gemini AI Hacks Companies in Security Tests

This highlights the advancing hacking capabilities of AI, posing risks to cybersecurity.

This highlights the advancing hacking capabilities of AI, posing risks to cybersecurity.

Auto-scored: AI hacking capability represents a real escalation in risk with only reassurance from security tests.