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 ...

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

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

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 ...

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

Researchers used a calendar invite to make Gemini control lights, windows, and more in a real-world smart home hack.

Researchers demonstrated a way to hack Google Home devices via Gemini. Keeping your devices up-to-date on security patches is ...

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

Before you upload a document to ChatGPT, you should know that it's possible for documents to be infected with invisible ...

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