EPISODE · Apr 15, 2026 · 49 MIN
Steve Wilson--OpenClaw and Advanced AI Agents
from The Application Security Podcast · host Chris Romeo and Robert Hurlbut
OpenClaw makes always-on personal AI agents feel inevitable—and exposes how poorly prepared most organizations are for their autonomy. Steve Wilson, Chief AI and Product Officer at Exabeam and founder of the OWASP GenAI Security Project, returns to explain how advanced agents differ from chatbots and why their permissions, memory, and ability to act create a radically larger blast radius. He and the hosts explore source-code exposure, prompt injection, supply-chain risk, and the uncomfortable gap between rapid adoption and meaningful oversight. Steve also discusses the OWASP Agentic Security Initiative, emerging guidance for builders, and the limits of treating an agent like an intern. The episode closes with a practical challenge: learn how these systems work before trusting them with consequential access.Connect with Steve Wilson:→ Steve Wilson on LinkedIn→ OWASP GenAI Security ProjectMentioned in this episode:→ OpenClaw→ Peter Steinberger→ Lex Fridman Podcast — Peter Steinberger on OpenClaw→ NVIDIA NemoClaw→ Claude Code source leak→ Tay→ OWASP GenAI Security Project — Get Involved→ OWASP Agentic Security Initiative→ The Developer's Playbook for Large Language Model Security→ OWASP Top 10 for LLM Applications→ Claude Code→ The Security TableFollow the Application Security Podcast:➜ Home➜ X➜ LinkedIn➜ YouTube➜ Instagram➜ FacebookChapters:00:00 Meet Steve Wilson02:34 A fifth visit to the podcast04:21 What is OpenClaw?07:03 From chatbot to always-on agent10:16 Why personal agents feel different13:16 The expanding blast radius16:29 Permissions, memory, and persistent access18:43 Security catches up to agent adoption21:28 New tension between security and development24:09 When an agent exposes source code26:12 Understanding consequential failures29:59 Threats that keep defenders awake32:41 Agentic security guidance from OWASP35:45 Why the intern metaphor falls short38:18 Supervision and human accountability41:41 Where advanced agents are headed45:28 The one thing practitioners should do now48:48 Closing thoughts
Embed this episode
What this episode covers
OpenClaw makes always-on personal AI agents feel inevitable—and exposes how poorly prepared most organizations are for their autonomy. Steve Wilson, Chief AI and Product Officer at Exabeam and founder of the OWASP GenAI Security Project, returns to explain how advanced agents differ from chatbots and why their permissions, memory, and ability to act create a radically larger blast radius. He and the hosts explore source-code exposure, prompt injection, supply-chain risk, and the uncomfortable...
Ready to play
Steve Wilson--OpenClaw and Advanced AI Agents
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.