Vulnerabilities Found in OpenAI's Atlas Browser Allow Code Injection and Memory Exploitation

Vulnerabilities Found in OpenAI's Atlas Browser Allow Code Injection and Memory Exploitation

First seen 2 Nov 2025, 16:14 UTC •TheregisterItnews.AuCsoonlineCyberscoopDarkreading •18.1

Article Content

Browse articles
ThreatCluster

Security researchers from LayerX have identified vulnerabilities in OpenAI's Atlas browser that enable attackers to inject malicious code and manipulate the browser's memory. This flaw allows for remote code execution and the deployment of malware, affecting users who adopt the AI-native browsing technology. The exploit requires user interaction, such as clicking a malicious link, to execute.

How this analysis works

Extracted Entities

1 / 2