Learn languages naturally with fresh, real content!

tap to translate recording

Explore By Region

flag Seven critical flaws in ChatGPT-4o and ChatGPT-5 let hackers steal data and hijack sessions with minimal user interaction, some still unpatched.

flag Tenable researchers have uncovered seven critical vulnerabilities in OpenAI’s ChatGPT-4o and ChatGPT-5, collectively named "HackedGPT," enabling attackers to steal data and hijack sessions via indirect prompt injection. flag Exploits can occur with zero or one user click, using malicious links or hidden code in web content, and include persistent memory injection that retains harmful commands across sessions. flag Some flaws remain unpatched, particularly in ChatGPT-5, allowing ongoing data leaks and safety bypasses. flag Researchers warn organizations to treat AI systems as active attack surfaces and implement strict controls, isolation, and monitoring.

11 Articles

Further Reading