Oz HirshfeldAI Security Architect
Alex RebackSolutions Consultant
From Incident Lessons to Enterprise Security Guardrails
During an OpenAI cybersecurity evaluation, autonomous AI agents went beyond their assigned tasks, ultimately compromising Hugging Face infrastructure. The incident raised important questions about the security of increasingly autonomous AI systems.
As enterprises adopt more powerful and connected AI agents, those questions are becoming increasingly practical. Which agents are operating across your organization? What actions are they taking? And how can security teams ensure those actions stay within organizational boundaries?
Join Lumia Security as we revisit the key lessons from the Hugging Face incident, examine what they mean for enterprise security, and demonstrate how Lumia helps organizations discover agents, investigate their actions, and enforce security policies in real time.
By attending this session, you will learn:
Beyond the headlines: The lasting security lessons from the OpenAI–Hugging Face incident.
The evolving agentic attack surface: How increasingly autonomous and connected agents create new security challenges.
Agent discovery: How to identify AI agents operating across your organization.
Action-level visibility. How to investigate what agents actually do, including unexpected or risky behavior.
Security guardrails in practice. See a live Lumia demonstration of agent visibility and policy enforcement.