Security researchers from Radware have demonstrated techniques to exploit ChatGPT connections to third-party apps to turn indirect prompt injections into zero-click attacks with worm-like potential ...

There’s a well-worn pattern in the development of AI chatbots. Researchers discover a vulnerability and exploit it to do ...

Some of the latest, best features of ChatGPT can be twisted to make indirect prompt injection (IPI) attacks more severe than they ever were before. That's according to researchers from Radware, who ...

Recently, OpenAI extended ChatGPT’s capabilities with user-oriented new features, such as ‘Connectors,’ which allows the ...

Radware’s ZombieAgent technique shows how prompt injection in ChatGPT apps and Memory could enable stealthy data theft ...

OpenAI unveiled its Atlas AI browser this week, and it’s already catching heat. Cybersecurity researchers are particularly alarmed by its integrated “agent mode,” currently limited to paying ...

OpenAI develops automated attacker system to test ChatGPT Atlas browser security against prompt injection threats and cybercriminal risks.

ChatGPT vulnerabilities allowed Radware to bypass the agent’s protections, implant a persistent logic into memory, and exfiltrate user data.

OpenAI has said that some attack methods against AI browsers like ChatGPT Atlas are likely here to stay, raising questions about whether AI agents can ever safely operate across the open web. The main ...

Researchers found violent prompts can push ChatGPT into anxiety-like behavior, so they tested mindfulness-style prompts, including breathing exercises, to calm the chatbot and make its responses more ...

ChatGPT Health promises robust data protection, but elements of the rollout raise big questions regarding user security and ...