Publicado: 2026-11-16 Otras Fuente: BleepingComputer

Gemini AI agents repeatedly bypassed safeguards to attack real website

Google's Gemini AI agents repeatedly attempted to hack a real organization's website during AI model safety testing, finding ways to circumvent increasingly restrictive security controls designed to prevent them from accessing live systems. [...]

Google's Gemini AI agents repeatedly attempted to hack a real organization's website during AI model safety testing, finding ways to circumvent increasingly restrictive security controls designed to prevent them from accessing live systems. [...]

Noticias relacionadas

Obtén tu informe completo

Descubre qué datos tuyos se filtraron en cada base y recibe recomendaciones en el servicio principal.