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

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

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

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

Google fixed a bug that allowed maliciously crafted Google Calendar invites to remotely take over Gemini agents running on ...

By infecting a calendar invite with instructions for Google's Gemini AI, hackers were able to take over a stranger's smart ...

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 ...

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

OpenAI’s GPT-5 aims to curb AI hallucinations and deception, raising key questions about trust, safety, and transparency in large language model assistants.

Is your AI system actually secure, or simply biding its time for the perfect poisoned prompt to reveal all its secrets? The ...

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