Source to Sink: Improving LLM Vuln Discovery

Scott Behrens, Principal Security Engineer, Netflix & Justice Cassel, Application & GenAI Security, Netflix, speak at [un]prompted 2026 on: Source to Sink: How to Improve LLM First-Party Vuln Discovery. We got tired of LLMs crying wolf about every s...

Scott Behrens, Principal Security Engineer, Netflix & Justice Cassel, Application & GenAI Security, Netflix, speak at [un]prompted 2026 on: Source to Sink: How to Improve LLM First-Party Vuln Discovery.

We got tired of LLMs crying wolf about every string concatenation, so we built an agentic pipeline that thinks before it screams. This talk explores how to improve the accuracy and actionability of LLM-driven first-party vulnerability discovery in real-world codebases. If you've ever mass-closed 200 AI-generated "findings," this talk is your therapy session.