Malicious Prompts Hidden in Data can Trigger Executable Payloads. Hackers can transform artificial intelligence-powered summarization tools into unwitting delivery agents for ransomware instructions through hidden code and prompt manipulation, security researchers warn. The method is an evolution of ClickFix, a social engineering tactic.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/ai-summaries-new-vector-for-malware-a-29299
