Get the app
Darren Meyer
Security research advocate at Checkmarx who researches AI-related software risks and authored the 'Bypassing AI Agent Defenses with Lies-In-The-Loop' study on prompt-injection and human-in-the-loop vulnerabilities.
Best podcasts with Darren Meyer
Ranked by the Snipd community
14 snips
Dec 20, 2025
• 25min
The lies that let AI run amok. [Research Saturday]
chevron_right
Darren Meyer, a Security Research Advocate at Checkmarx, dives into the alarming world of AI vulnerabilities. He introduces 'lies-in-the-loop,' a technique that tricks developers into approving risky AI actions masked as harmless. Using examples with AI code assistants like Claude Code, he explains how prompt injection can lead to catastrophic consequences like remote code execution. With rising AI adoption, he stresses the critical need for better security awareness and protective measures in developer workflows.
The AI-powered Podcast Player
Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
Get the app