Black Hat , AI/ML , Application security Frank Vukovits on how Delinea delivers runtime authorization for AI agents August 6, 2026 Share By SC Staff As AI agents move from experiments to autonomous operators inside production databases, cloud consoles, and Kubernetes clusters, enterprises face a new problem: agents with legitimate credentials taking actions no one authorized. Frank Vukovits, Chief Security Scientist at Delinea, breaks down why verifying access at connection time is no longer enough and what it takes to enforce policy on every agent action before it executes. He explains how runtime authorization closes the gap between hiding credentials and actually controlling what agents do once they're inside a session. This segment is sponsored by Delinea. Visit https://securityweekly.com/delineabh to learn more about them! Show Notes: https://securityweekly.com/bh26-1 An In-Depth Guide to AI Get essential knowledge and practical strategies to use AI to better your security program. Learn More SC Staff Related Black Hat Intruder’s Chris Wallis on AI pentesting and the future of cybersecurity SC Staff August 6, 2026 Wallis dives into the nuances of AI-enabled security and how these offerings will impact midmarket security teams. Black Hat Ido Geffen on why Novee owns the full AI pentesting stack SC Staff August 6, 2026 Novee's Geffen breaks down what it means to own the full AI pentesting stack. Black Hat Ramin Farassat on how Menlo Security is securing AI agents from prompt injection SC Staff August 6, 2026 Farassat discusses how security teams can put controls on the agent attack surface without blocking agentic AI outright. Get daily email updates SC Media's daily must-read of the most current and pressing daily news Business Email By clicking the Subscribe button below, you agree to SC Media Terms of Use and Privacy Policy . Subscribe Related Terms Banner Browser Cache Cramming Common Gateway Interface (CGI) Client Cookie DLL Injection Dynamic Link Library You can skip this ad in 5 seconds