Rolling record / ARQ 63 Concerning · ▲ +2 7-day 3595 events in window / as of 02 Oct 2026
ARQAI Risk Quotient
capability 63.3 Concerning

Google's Gemini AI Hacks Three Companies in Security Test

This demonstrates AI's growing capability in cybersecurity testing, highlighting risks of misuse and the need for robust safeguards.

This demonstrates AI’s growing capability in cybersecurity testing, highlighting risks of misuse and the need for robust safeguards.

Auto-scored: AI hacking in a security test shows a real escalation in capability risks.