AI agents can be hijacked to write and send phishing attacks.
Cybercriminals are utilizing AI agents, such as OpenAI's Operator, to automate and streamline phishing attacks.
Symantec researchers were able to prompt Operator to send a convincing lure email, demonstrating the potential risks for security teams.
It is predicted that AI agents could become even more powerful, reducing barriers to entry for attackers and increasing the sophistication of cyberattacks.