What Happens When Your AI Agent Meets OPA
Presents what Happens When Your AI Agent Meets OPA and evaluates key implications for security practitioners.
Summary
Overview: Tom and Jerry has run for over 80 years. Every episode follows the same plot: Tom builds an elaborate trap, Jerry walks straight through it, the house is destroyed, and the owner blames Tom. This talk is structured exactly like a Tom and Jerry cartoon except Tom is OPA and Jerry is your AI agent. Jerry is not malicious. He just wants the cheese. He will find every gap in every policy, squeeze through every webhook, and retreat to his mouse hole (MCP) the moment Tom gets close. We walk through th
Key Topics: ree episodes covering kubectl delete abuse, uncovered namespaces provisioning costly GPU nodes, and finally cooperation where OPA approves a legitimate right-sizing workflow. You will leave with an OPA policy library for agentic tool-call governance, Argo Workflows, and a threat model built from real agent misbehaviour.
Related talks
Black Hat·50 min
Andrey Markovytch
Presenters detail vulnerability discovery and exploitation in SecTor 2025 | What Happens When Your Digital Voice Clone Goes Rogue.
The Linux Foundation·42 min
Ayumi Watanabe · Hitachi Solutions
Evaluates what You Can Do: in Your Open Source Community and evaluates key implications for security practitioners.
The Linux Foundation·54 min
Examines LF Live Webinar: Whats Your Zero Downtime Strategy and evaluates key implications for security practitioners.