Researchers detail how a prompt injection attack bypassed Apple Intelligence protections
09/04/2026-23:39 09/04/2026-23:40 מחשבים וטכנולוגיה 9to5Mac דיווח
A now corrected issue allowed researchers to circumvent Apple’s restrictions and force the on-device LLM to execute attacker-controlled actions. Here’s how they did it. 9to5mac.com
