Full-day, multi-track program features keynotes, panels, and sessions shaped by more than 100 community submissions

Zenity Labs today announced the details of its second AI Agent Security Summit, taking place October 8, 2025 at the Commonwealth Club in San Francisco.

Building on the success of the debut event in New York City earlier this year, the San Francisco summit expands into a larger program with multiple tracks and a broader lineup. Designed as a community event for the League of Security Experts, the summit will bring together researchers and practitioners to confront the risks of AI agents. With no product pitches or vendor showcases, the program is dedicated to knowledge sharing, original research, and open discussion to shape the future of AI agent security.

The San Francisco Summit will feature discussions on adversarial AI, red teaming, runtime defenses, and applied case studies while spotlighting new research from enterprise practitioners and independent researchers. Featured speakers include those listed below with more to come:

• Kandi Abhishek, Nokia - “When Trust Backfires: Exploiting Gemini CLI’s Illusion of Shell Safety leading to Code Execution”
• Michael Bargury, Zenity - Keynote Speaker and AI Agent Platform Panel Moderator
• Jack Cable, Corridor - “A Case Study of Vulnerabilities in AI Agents”
• David Campbell, Scale AI - “Ignore Previous Instructions: Embracing AI Red Teaming”
• Emile Delcourt, Panorama - “Genetic Evolution in Adversarial Prompting: Subverting an AI Guard”
• Amanda Grady, ServiceNow - AI Agent Platform Panelist
• Allie Howe, Growth Cyber - “Agentic Threats: From Theory to Practice”
• Ken Huang, Distributedapps.AI - AIVSS Panel Moderator
• Nate Lee, Trustmind - “My AI is an INTJ: Understanding the Personality Traits of Your Autonomous Agents”
• Jiquan Ngiam, MintMCP - “X-Ray for Agents: Observability & Safe Tooling for MCP”
• Rashmi Nagpal, Patchstack - “Code Guardian: Building Multi-Agent AI Systems for Autonomous Security Operations”
• Ryan Ray, Slalom - “Securing Agentic AI: Threats, Models, and Mitigation in the Age of Autonomy”
• Vamsi Krishna Reddy, Walmart - “AI Agent Attack Vectors: Unveiling Self-Healing Vulnerabilities in Enterprise Systems”
• Steve Wilson, Exabeam - “Agents as Insider Threats: Securing Against Your Fastest, Sneakiest Employees”

“AI agents have grown arms and legs, they're not just processing data, they're taking actions with the same privileges as your most trusted employees. The problem? They have no moral compass, no accountability, and attackers need very little to turn them into agents of chaos,” said Michael Bargury, co-founder and CTO of Zenity. “This Summit is where the League of Security Leaders comes together to share research, challenge assumptions, and define how enterprises can secure AI Agents at the edge of autonomy.”

Event Details

• Date: October 8, 2025
• Location: The Commonwealth Club, San Francisco, CA
• Registration: https://zenity.io/resources/events/ai-agent-security-summit-2025

About Zenity

Zenity is the first and only AI agent security platform, empowering enterprises to adopt AI agents with confidence. By providing observability, governance, and defense across the AI lifecycle, Zenity ensures organizations stay ahead of risks while harnessing the full potential of AI.

View source version on businesswire.com: https://www.businesswire.com/news/home/20250903383876/en/

This Summit is where the League of Security Leaders comes together to share research, challenge assumptions and define how enterprises can secure AI Agents at the edge of autonomy.