“They can think for themselves. They can decide how to do a task, which may be different than what you intended. They can grant privileges to each other. They can decide that they want to access something that you didn’t want them to access just because they need it to complete a task. They’re doing it with your credentials or your identity.” – Avihay Nathan, Senior Vice President of CyberArk, describing agentic A.I. risks
Read the full article here