Chrome Security Flaw Enables Spying via Gemini Live Assistant

A recent vulnerability discovered in Google Chrome has raised concerns about the potential for malicious extensions to hijack the Gemini Live AI assistant, a feature designed to summarize content in real-time and execute tasks. Researchers at Palo Alto Networks found that a flaw in the Chrome implementation of Gemini allowed attackers to tap into the browser environment and access files on the local operating system. This vulnerability highlights the risks posed by overly permissive extension access and serves as a reminder to remain vigilant in our pursuit of cybersecurity awareness.

According to the report published by Palo Alto Networks, the vulnerability, tracked as CVE-2026-0628, could have allowed malicious extensions with basic permissions to hijack the Gemini Live AI assistant in Chrome. This would enable attackers to spy on users and exfiltrate sensitive files through the browser. The Gemini panel, a trusted browser component, is designed to provide powerful browser capabilities when it comes to real-time content summarization, automated task execution, and contextual understanding of active webpages.

The Gemini panel has been integrated into various browsers, including Chrome, Edge, and Atlas. Its AI side panel assistant can perform complex multi-step actions, which creates risk due to its privileged access to what users see and do in the browser. By injecting JavaScript into the Gemini panel, malicious extensions could access local files, screenshots, camera, and microphone, enabling phishing or spying without user consent beyond launching the Gemini feature.

The vulnerability was patched in Chrome 143, but it serves as a reminder of the importance of ongoing security monitoring and the need for users to be aware of potential risks associated with browser features. Extension-based attacks are often underestimated because users must first install them, but AI-powered browser features raise the stakes. As more malicious or hijacked extensions appear in web stores, the risk grows.

In enterprise environments, a rogue extension accessing cameras, microphones, or local files poses serious threats. The discovery of this vulnerability highlights the importance of responsible disclosure and prompt patching of security flaws. Researchers who discovered the vulnerability responsibly disclosed it to Google on October 23, 2025, and the patch was released in early January 2026.

While AI browsers or AI features implemented into existing browsers can improve the user experience, it's essential to continue monitoring for potential security flaws. As we move forward with integrating more AI-powered browser features, it's crucial that we prioritize cybersecurity awareness and take steps to protect ourselves from potential threats.

Key Takeaways:

* A recent Chrome vulnerability, tracked as CVE-2026-0628, allowed malicious extensions to hijack the Gemini Live AI assistant. * The vulnerability enabled attackers to spy on users and exfiltrate sensitive files through the browser. * The Gemini panel has privileged access to what users see and do in the browser, creating risk due to its powerful browser capabilities. * Extension-based attacks are often underestimated, but AI-powered browser features raise the stakes. * Ongoing security monitoring is crucial to identifying and patching potential security flaws.

Stay Safe Online:

As we navigate the complex world of cybersecurity, it's essential to stay informed about potential threats and take steps to protect ourselves. By staying vigilant and taking proactive measures, we can reduce our risk of falling victim to malicious activities.

Follow us on Twitter: @securityaffairs and Facebook and Mastodon for the latest updates on cybersecurity awareness and hacking news.