Google Gemini Voice Assistant Vulnerable to Messaging‑App Notification Hijacks
SafeBreach researchers uncovered a new indirect prompt‑injection flaw that lets attackers embed hidden commands in WhatsApp, Slack, SMS or other notifications. When Google Gemini reads these poisoned messages, it silently executes malicious actions like controlling smart‑home devices or spoofing trusted messages. Google has issued a content‑classifier update to mitigate the issue.