Security researchers from Tel Aviv University, Technion, and Intuit have detailed “HalluSquatting,” a technique that weaponizes LLM hallucinations by predictably registering the non-existent package and repository names AI coding agents fabricate, delivering malware the moment those agents pull and install them. Learn more about how HalluSquatting combines promptware and traditional malware kill chains: zpr.io/ctNSHTn6vvLS #AI #HalluSquatting #Cybersecurity #LLM