New hack exploits AI hallucinations to trick agents into running malicious code — 'HalluSquatting' attack exploits a fundamental weakness in every available model

Read full story on Tom's Hardware
Share
New hack exploits AI hallucinations to trick agents into running malicious code — 'HalluSquatting' attack exploits a fundamental weakness in every available model
AI disclosure

Summary

Attackers can exploit how AI bots hallucinate software URLs to create massive botnets. The vulnerability is endemic to every model.

Original reporting

Open original source
Read full article on Tom's Hardware

Get the AFBytes Brief

Major stories, AI-assisted analysis, and what to watch next. Free, monthly, unsubscribe anytime.