HalluSquatting attack exploits AI hallucinations to trick agents into running malicious code, building botnets.

Attackers exploit AI chatbots' tendency to hallucinate software URLs to trick them into downloading malicious code. This 'HalluSquatting' technique can assemble massive botnets. The vulnerability affects all major AI models.

• New hack exploits AI hallucinations to trick agents into running malicious code — 'HalluSquatting' attack exploits a fundamental weakness in every available model
• Hackers can use 9 of the most popular AI tools to assemble massive botnets