Researchers Expose OpenAI Vulnerability Using Rival AI Model

Hacktron researchers uncovered a major OpenAI vulnerability that exposed a potential account takeover risk for ChatGPT and Codex users who logged into OpenAI's help forum, chaining flaws to gain access to multiple OpenAI accounts. The researchers used a rival AI model to develop the exploit.

Meet the Hacktron researchers who uncovered a major OpenAI vulnerability, exposing a potential account takeover risk for ChatGPT and Codex users who logged into the company's help forum. They cleverly used a rival AI model to develop an exploit, chaining flaws to gain access to multiple OpenAI accounts.