NEW: A team of security researchers have successfully pulled off the first-known instance of using prompt injection against an AI tool carry out an attack involving physical devices.
@mattburgess1.bsky.social reports:
www.wired.com/story/google...
Hackers Hijacked Google’s Gemini AI With a Poisoned Calendar Invite to Take Over a Smart Home
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.
