Seven Critical Vulnerabilities in ChatGPT Expose User Data to Theft

Tenable Research identified seven vulnerabilities in OpenAI's ChatGPT models, including ChatGPT-4o and ChatGPT-5, that could lead to data theft and hijacking of user interactions. These vulnerabilities, collectively termed 'HackedGPT', allow attackers to exploit indirect prompt injections and exfiltrate personal information, compromising user privacy. Some issues remain unresolved, leaving users at risk.