Researchers from Zenity have found multiple ways to inject rogue prompts into agents from mainstream vendors to extract ...

Security researchers found a weakness in OpenAI’s Connectors, which let you hook up ChatGPT to other services, that allowed ...

A prompt injection attack using calendar invites can be used for real-world effects, like turning off lights, opening window ...

For likely the first time ever, security researchers have shown how AI can be hacked to create real world havoc, allowing ...

A new theoretical attack described by researchers with LayerX lays out how frighteningly simple it would be for a malicious or compromised browser extension to intercept user chats with LLMs and ...

Now fixed Black hat  A trio of researchers has disclosed a major prompt injection vulnerability in Google's Gemini large ...

Researchers bypass GPT-5 guardrails using narrative jailbreaks, exposing AI agents to zero-click data theft risks.

OpenAI's ChatGPT can easily be coaxed into leaking your personal data — with just a single "poisoned" document. As Wired ...

Attackers could silently modify sensitive MCP files to trigger the execution of arbitrary code without requiring user ...

Zenity shows AI assistants such as ChatGPT, Copilot, Cursor, Gemini, and Salesforce Einstein can be abused using specially ...

Cybersecurity researchers were able to control smart home devices by hacking the Google Gemini artificial intelligence assistant.

The hack, laid out in a paper titled “Invitation Is All You Need!”, the researchers lay out 14 different ways they were able ...