AI Security

    Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts

    Unpatched zero-click vulnerabilities allow attackers to hijack AI agents through automated prompt injection.

    Zenity researchers reported the findings to Anthropic and OpenAI in late 2025 and early 2026, but they remain unpatched. The post Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts appeared first on SecurityWeek.

    SA

    SecurityWeek AI

    Source

    Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts
    AI Analysis

    Generated insight by OnAirToday AI

    These zero-click vulnerabilities demonstrate that AI agents are becoming primary attack vectors by automatically processing malicious content from standard communications. Because these flaws remain unpatched, users are susceptible to data theft simply by interacting with AI interfaces that execute hidden instructions.

    Powered by AI • Not a substitute for human analysisMore Insights →
    Read the full story at SecurityWeek AI →
    Share
    Filed under:AI Security

    Comments

    Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.

    0/1000