An agent doesn’t need an attacker to do something you wouldn’t have approved.
In this Research Live session, Origin researcher Tyler Holmwood walks through how agents go off course. He follows real traces to show what the agent was asked to do, which instructions it followed, and how its actions crossed a line.
He covers how to recognize risky behavior, review what your agents can access, and use controls you already own to limit the consequences.

Tyler Holmwood
Staff Security Researcher, Origin Technology