AI agents are relentless. Unlike human developers, an agent can test thousands of permission paths in seconds, turning an innocent request for a “quick proof of concept” into a major security event. In this live session, we demonstrate how developers using agentic AI to solve real-world problems can inadvertently trigger the creation of unauthorized roles and access points.
Jeff Moncrief, Field CTO @ Sonrai, walks through a live AWS environment to show how a developer can introduce overprivilege by using an agent for a benign task that requires it to gather additional privileges. He’ll walk through why existing RBAC isn’t catching this problem, available guardrails in cloud native IAM toolkits, and how Cloud Permissions Firewall acts as a final defensive layer. You will see how automated “Default Deny” policies block agents from creating new identities or ingress points, ensuring your team can innovate at machine speed without leaving the internal doors of your cloud unlocked.
Meet Your Speaker
Jeff Moncrief
Field CTO
Sonrai Security
Killchain killer for 25 years
Register now
- Instant confirmation email
- No spam, unsubscribe anytime
By registering, you agree to receive webinar updates and marketing emails. You can opt-out at any time.