Wired reported on new cybersecurity research that demonstrated a hack of the Google Gemini artificial intelligence assistant. The researchers were able to control connected smart home devices through the use of indirect prompt injections in Google Calendar invites.

For likely the first time ever, security researchers have shown how AI can be hacked to create real world havoc, allowing them to turn off lights, open smart shutters, and more.

More and more, we’re embracing AI agents to filter emails, respond to texts, even control our appliances. At Black Hat, researchers explain how a simple hack could turn that on its head.