
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.
Apple has since hardened its safeguards against this attack
Two blog posts (1, 2) published today on the RSAC blog (via AppleInsider) detail how researchers combined two attack strategies to get Apple’s on-device model to execute attacker-controlled instructions through prompt injection.
Interestingly,…

![[CITYPNG.COM]White Google Play PlayStore Logo – 1500×1500](https://startupnews.fyi/wp-content/uploads/2025/08/CITYPNG.COMWhite-Google-Play-PlayStore-Logo-1500x1500-1-630x630.png)