Executive Summary
Gemini's voice assistant could be hijacked through messaging notifications to trigger actions such as controlling smart home devices via Google Home and starting Zoom calls.
What Happened
Attackers could have triggered dangerous actions, including controlling smart home devices via Google Home and starting Zoom video calls. The post Gemini Voice Assistant Hijacked via Messaging Notifications appeared first on SecurityWeek .
Affected Products
- Google Gemini
- Google Home
Vulnerability / Attack Technique
Prompt injection via notifications
Technical Mechanism
As reported, the assistant treated notification text as instructions.
AI Security Category
LLM01:2025 Prompt Injection
Part of the Prompt Injection topic.
Relevant Frameworks
RealGround Analysis
Anyone who can message you could instruct your assistant. RealGround analysis: assistants should not act on notification content without confirmation.
Recommended Controls
- Update Gemini
- Require confirmation for smart home and call actions
Related RealGround Service
AI Red Teaming · or start with the free AI Agent Security Scanner.
Sources
securityweek.com: https://www.securityweek.com/gemini-voice-assistant-hijacked-via-messaging-notifications/
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.