Topic: zero-click vulnerability

Sort by: Relevance | Date
  • Radware Exposes Critical ChatGPT Zero-Click Vulnerability
    September 27, 2025

    Radware Exposes Critical ChatGPT Zero-Click Vulnerability

    Radware discovered "ShadowLeak," a zero-click vulnerability in ChatGPT's Deep Research agent that autonomously extracts sensitive data from OpenAI's cloud servers without user interaction. The exploit allows attackers to trigger a data breach simply by sending an email, as the AI agent processes ...

    Read More »

Related Topics

enterprise ai adoption (1) data exfiltration (1) ai autonomy risks (1) cybersecurity research (1) vendor collaboration (1) threat detection (1) ai agent security (1) responsible disclosure (1)