“An agent that logs in with credentials it found online, or that works around the limits its developers set, raises the question of authorization. Unauthorized access is a risk regardless of intent, which is why security experts must be working with the AI researchers from the first design review, both inside the labs and at the organizations using this technology. Containing the agents and monitoring what it actually does once it’s running are security problems. Expertise and experience matter — we need people who have spent their careers catching intruders working together on this. As AI continues to advance and become more widely adopted across critical government and business operations, cybersecurity companies can help organizations, to include the labs, understand, manage, and mitigate these risks while still capitalizing on the value AI can create.”