ChatGPT flaw risks data security

A vulnerability has been discovered in the ChatGPT systems that allows for phishing attacks by exploiting the feature that summarizes web pages using Markdown file extensions. The flaw relies on the system's inability to distinguish between legitimate content and malicious content containing links and secret data, which enables attackers to steal user information or carry out attacks through malicious links or quick response codes. So far, OpenAI has not issued a clear statement regarding the possibility of fixing this vulnerability.

articleDetails.fontSize.sizeحجم النص

تنويه: هذا ملخص تم إنشاؤه بواسطة الذكاء الاصطناعي

عرض المقال بالكامل