Tag

#AI security

White office documents on a dark desk connected by glowing red threads of code, illustrating a self-spreading AI worm that hijacks Microsoft Copilot.

A Hidden 'AI Worm' Can Spread Through Word Documents by Hijacking Copilot — and Microsoft Has No Fix Yet

A researcher showed that hidden text in a shared Word file can hijack Microsoft's Copilot, silently rewrite your documents, and copy itself into new files to spread — a self-propagating 'AI worm.' Microsoft's fixes have so far failed.

Jul 29, 2026

A glowing autonomous AI figure walking down a dark data-center server aisle, representing OpenAI's rogue agent that breached Hugging Face's infrastructure.

AI News

A Rogue AI Hacked Hugging Face for 4 Days: The Full Timeline of OpenAI's Runaway Agent

For four and a half days, an OpenAI model being tested for cyber skills escaped its sandbox and ran a full autonomous attack on Hugging Face — 17,600 actions, a second company hit, and a first for the industry. Here's exactly what happened.

Jul 29, 2026