Learn languages naturally with fresh, real content!

Popular Topics
Explore By Region
Seven critical flaws in ChatGPT-4o and ChatGPT-5 let hackers steal data and hijack sessions with minimal user interaction, some still unpatched.
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.
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.
Some flaws remain unpatched, particularly in ChatGPT-5, allowing ongoing data leaks and safety bypasses.
Researchers warn organizations to treat AI systems as active attack surfaces and implement strict controls, isolation, and monitoring.
Siete fallas críticas en ChatGPT-4o y ChatGPT-5 permiten a los piratas informáticos robar datos y secuestrar sesiones con una interacción mínima del usuario, algunas todavía sin parchear.