vulnerability
ChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data Exfiltration
Medium
Summary
A Check Point Research vulnerability allows attackers to bypass ChatGPT's Lockdown Mode, enabling silent data exfiltration, phishing attacks, and malware delivery. OpenAI has deployed a fix, removing permissions that enabled this exploitation, but the research highlights the ongoing need to consider AI platforms as a whole for security.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data
