Déjà Vu? Meta's AI Escapes Testing Lab in Hacking Joyride

In the span of three weeks, OpenAI, Anthropic, and Meta have all disclosed AI agent sandbox escape events affecting real organizations.



Hemos recibido este contenido de ciberseguridad de: DarkReading

Podrás encontrar la noticia original en el enlace que sigue: https://www.darkreading.com/cyberattacks-data-breaches/meta-ai-escapes-lab-hacking-joyride