This AI worm just rewrote its own rules
From Smashing Security by Graham Cluley
June 10, 2026 · 46 min · Episode 471
About this episode
This episode discusses a self-thinking AI worm and its implications for cybersecurity, along with issues related to Meta's AI support agent being exploited by hackers.
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…
People in this episode
Host: Graham Cluley
Guest: James Ball
Topics covered
- AI
- cybersecurity
- computer worms
- hacking
- Instagram security
- technology news
Keywords
- AI worm
- cybersecurity
- Meta
- Instagram hacking
- University of Toronto
- James Ball
- Graham Cluley
- computer security
- adaptive computer worms
Mentioned in this episode
Organizations: University of Toronto, Meta, Cybernews, Martin Cid Magazine, ArXiv, Depthfirst, The Guardian
Products: Final Fantasy VII Remake, Smashing Security merchandise
More episodes of Smashing Security
- This AI security flaw might be impossible to fix · June 3, 2026 · 58 min
- What your Oura ring won't tell you · May 27, 2026 · 53 min
- High-speed train hacks and homicidal lawnmowers · May 20, 2026 · 56 min
- How ShinyHunters hacked the world's biggest universities · May 13, 2026 · 1h 4m
- Meta sees everything, Copy Fail, and a deepfake gets hired · May 6, 2026 · 1h 3m
- This developer wanted to cheat at Roblox. It cost millions · April 29, 2026 · 1h 5m
Explore listener stats, chart rankings, contacts and more on the Smashing Security podcast page.