Hidden prompts on malicious websites trick AI agents into making payments or trusting fake sites, exposing new risks for autonomous AI workflows. Zscaler ThreatLabz documented two active campaigns that embed hidden instructions in web pages to manipulate AI agents, not human users, though those get caught too. The technique is called indirect prompt injection: malicious […]
First seen on securityaffairs.com
Jump to article: securityaffairs.com/194822/ai/hidden-web-prompts-trick-ai-agents-into-sending-money.html
