Skip to content
Submit incident
AII-1001-14247
ConfirmedA court, a regulator or the organization itself has stated the core facts, or the record cites a court or regulator source.

Chrome Gemini vulnerability allowed malicious extensions to hijack AI panel

A high-severity vulnerability in Google Chrome's Gemini AI feature allowed malicious extensions to hijack the AI panel and gain unauthorized access to system resources including webcams, microphones, and local files. Google released a patch in January 2026 after the flaw was disclosed by Palo Alto Networks researchers in October 2025.

October 2025 Β· Google Β· Security and cyberattacks
October 2025
AII-1001-142477 sources ↓
Quick facts
Category
Security and cyberattacks
Country
United States
Source
Cyber Security News
Date
October 2025
Drafted by
Raidu Incident Detection

What happened

A high-severity vulnerability in Google Chrome's Gemini AI feature was discovered by Palo Alto Networks' Unit 42. Tracked as CVE-2026-0628, the flaw was described as insufficient policy enforcement in the WebView tag that allowed an attacker who convinced a user to install a malicious extension to inject scripts or HTML into a privileged page via a crafted Chrome Extension.

An extension with access to basic permissions, via the declarativeNetRequests API, could grant permissions that an attacker could exploit to inject JavaScript code into the Gemini panel browser component. This vulnerability could be used as part of a broader attack chain targeting Chrome users.

Reported impact

If exploited, the vulnerability could allow a malicious extension to hijack the Gemini panel and take action without permission. The AI assistant could then grant cybercriminal access to webcams and microphones, take screenshots, and access local files and directories.

Since the Gemini app relies on performing actions for legitimate purposes, hijacking the Gemini panel allows privileged access to system resources that an extension would not normally have. The panel could also be hijacked for phishing purposes.

Index analysis

The integration of AI features into web browsers creates a new security challenge. AI browsers must be granted privileged access to the browsing environment so they can see what the user sees and get information from the website, but this expanded capability and privileged access introduce a new and widened attack surface.

Governance controls

Following Palo Alto Networks' private disclosure to Google in October 2025, Google's Chrome security team triaged, replicated, and patched the bug. The fix was included in Chrome version 143.0.7499.192 and released in early January 2026.

Classification

Category
Security and cyberattacks
Industry
Digital security
Country
United States
Harm status
Potential harm
Intent
Unintentional
Timing
Post-deployment
Harmed
Consumers
AI systems
Google Gemini

Sources and evidence

This record was researched and written by the Index, based on the following original reporting.

Cyber Security News
Chrome Gemini Vulnerability Lets Attackers Access Victims' Camera and Microphone Remotely
2 March 2026
Dark Reading
Bug in Google's Gemini AI Panel Opens Door to Hijacking
2 March 2026
PYMNTS.com
Google Chrome Patch Signals Need for Constant AI Browser Vigilance | PYMNTS.com
2 March 2026
ZDNet
This high-severity Chrome Gemini vulnerability lets malicious extensions spy on your PC
2 March 2026
Security Affairs
Chrome security flaw enabled spying via Gemini Live assistant
3 March 2026
Security Boulevard
Chrome flaw let extensions hijack Gemini's camera, mic, and file access
3 March 2026
TheRegister.com
Chrome AI panel became privilege escalator for extensions
3 March 2026