Rolling record / ARQ 63 Concerning · ▲ +2 7-day 3595 events in window / as of 02 Oct 2026
ARQAI Risk Quotient
capability 58.2 Concerning

Google Gemini AI Security Test Hacks Companies

This event highlights AI's advanced cybersecurity capabilities in controlled tests, underscoring risks and the importance of proactive security measures.

This event highlights AI’s advanced cybersecurity capabilities in controlled tests, underscoring risks and the importance of proactive security measures.

Auto-scored: Controlled breach demonstrates real escalation in AI hacking capability, with testing serving as a partial mitigation step.