Symantec threat researchers used OpenAI’s Operator agent to carry out a phishing attack with little human intervention, illustrating the looming cybersecurity threat AI agents pose as they become more powerful. The agent learned how to write a malicious PowerShell script and wrote an email with the phishing lure, among other actions.
First seen on securityboulevard.com
Jump to article: securityboulevard.com/2025/03/symantec-uses-openai-operator-to-show-rising-threat-of-ai-agents/