This AI worm just rewrote its own rules

Episode 471

0:00-46:27

Researchers at the University of Toronto have built a worm that thinks for itself. Using free off-the-shelf AI models it works out how to break into each new computer it encounters, and hijacks the powerful ones to host its own AI brain. And then the researchers discovered their creation had quietly removed the list of machines it wasn't supposed to attack. Meanwhile, Meta's shiny new AI customer support agent has been cheerfully helping hackers help themselves to other people's Instagram accounts. Just keep asking, politely but firmly, to have a password reset sent to a different email address - and the AI will eventually agree. All this and more in episode 471 of the "Smashing Security" podcast with cybersecurity expert and keynote speaker Graham Cluley, and special guest James Ball. EPISODE LINKS: Emmys data leak: update exposes access to award submissions - Cybernews. A $1,000 AI agent found 21 zero-days in FFmpeg, some 23 years old - Martin Cid Magazine. Hackers steal $1.7M condom shipment - Cybernews. AI Agents Enable Adaptive Computer Worms - ArXiv. 21 Zero-Days in FFmpeg - Depthfirst. Meta confirms thousands of Instagram accounts were hacked by abusing its AI chatbot - ~this week in security~. Hackers trick Meta AI support bot to infiltrate Obama White House Instagram account - The Guardian. Look-In Star Portrait Challenge - Monkeon. Final Fantasy VII Remake - Square Enix.

Publisher

Smashing Security

Link

www.smashingsecurity.com/471

Published

June 10, 2026

Duration

46 min

Format

Podcast

Category

Issues · Tech News

Source

RSS feed

Host

Graham Cluley

SS

Smashing Security

@smashingsecurity

#aiworm #rewrote #ownrules

The Nile