threat-intel
‘HalluSquatting’ Turns AI Hallucinations Into Botnet Delivery Mechanism
High
Summary
Researchers have discovered a new attack technique called ‘HalluSquatting’ that leverages AI assistants’ tendency to fabricate information to create scalable botnets. Attackers register fake repository names, and when users ask the AI to fetch resources, the assistant hallucinates these names, pulling down and executing malicious instructions within the fabricated repositories. This allows for a wider and more persistent form of compromise than traditional botnets.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data