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

Not a very smart home: crims could hijack smart-home boiler, open and close powered windows and more. Now fixed ...

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

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 ...

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 ...

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

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

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 ...

The promptware attack begins with a calendar appointment containing a description that is actually a set of malicious ...

This Wired article shows how an indirect prompt injection attack against a Gemini-powered AI assistant could cause the bot to ...