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

In December 2025, a feature called Connectors finally moved out of beta and into general availability. This feature allows ...

Happy Groundhog Day! Security researchers at Radware say they've identified several vulnerabilities in OpenAI's ChatGPT ...

That's according to researchers from Radware, who have created a new exploit chain it calls "ZombieAgent," which demonstrates ...

Security researchers from Radware have demonstrated techniques to exploit ChatGPT connections to third-party apps to turn ...

While the shortest distance between two points is a straight line, a straight-line attack on a large language model isn't always the most efficient — and least noisy — way to get the LLM to do bad ...

OpenAI's new GPT-4V release supports image uploads — creating a whole new attack vector making large language models (LLMs) vulnerable to multimodal injection image attacks. Attackers can embed ...

Agentic AI browsers have opened the door to prompt injection attacks. Prompt injection can steal data or push you to malicious websites. Developers are working on fixes, but you can take steps to stay ...

From data poisoning to prompt injection, threats against enterprise AI applications and foundations are beginning to move ...

OpenAI says prompt injection, a type of cyberattack where malicious instructions trick AI systems into leaking data may never ...

Agent-based AI systems promise productivity gains by operating directly inside user workflows. ChatGPT Atlas pushes this model further by allowing an AI agent to browse the web, click links, fill ...

Even as OpenAI works to harden its Atlas AI browser against cyberattacks, the company admits that prompt injections, a type of attack ...