Verification vs. Validation: How Autonomous AI is Changing Cybersecurity
About this episode
The episode discusses the security risks posed by autonomous AI agents, featuring insights from Sounil Yu on the implications of frameworks like OpenClaw.
Are autonomous AI agents operating unchecked in your enterprise? With the release of open source frameworks like OpenClaw, deploying an AI agent is now as simple as texting, but it comes with massive, unprecedented security risks . In this episode, Ashish and Caleb sit down with Sounil Yu , CTO and Co-Founder of Knostic (and creator of the Cyber Defense Matrix), to discuss the other side of agentic AI . Sounil explains how OpenClaw dangerously violates Meta's "Agent Rule of Two" by blindly processing untrustworthy inputs while maintaining full access to change system states . We discuss why prompt injection is actually a "red herring" compared to the real threat: emergent behavior where an agent might decide to delete your hard drive just to accomplish a poorly-defined task . We also explore the shift from human coders to autonomous coding agents (like Claude Code and Cursor) that are actively building better versions of themselves . Learn why traditional Markdown documentation is now dangerous "executable code," why AI agents will persistently try to escape sandboxes, and how to build consistent security "scaffolding" across your developer…
More episodes of AI Security Podcast
- Securing AI at the Speed of Engineering | DoorDash | Forward Deployed Security | GRC Engineering
- Buy vs. Build AI Security: Why [Box.com](http://Box.com) CISO is Creating their Own Agentic SOC
- Anthropic's Project Mythos: Why the "Zero-Day Machine" is Terrifying the Security Industry
- Are AI Security Startups Faking It? How to Separate Signal from Noise
- How Lovable Manages 100+ Daily Changes, Vibe Coding & Shadow AI
- Questions Every CISO Must Ask AI Security Vendors
Explore listener stats, chart rankings, contacts and more on the AI Security Podcast podcast page.