Industry Leaders from Electronic Arts, Exabeam, Google, OpenAI, ServiceNow, Slalom, Stanford University, Walmart to Present on Securing AI agents

Zenity, the leading end-to-end security and governance platform for AI agents, today announced the full agenda for the upcoming AI Agent Security Summit 2025, taking place on October 8, 2025, at the Commonwealth Club in San Francisco. See the full agenda graphic above.

This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20250918300679/en/

Zenity announces the full agenda for the AI Agent Security Summit, taking place Oct. 8, 2025 in San Francisco.

The one-day, multi-track program features 3 keynotes, 6 sessions, 6 lightning talks and 2 panels shaped by more than 100 community submissions. This event brings together security leaders and experts from across the community to present original work and share practical strategies for securing AI agents throughout enterprise environments.

The agenda addresses today’s most pressing enterprise risks, including vulnerabilities in coding agents, insider threats, prompt injection, adversarial prompting and governance challenges AI adoption. From case studies and red teaming exercises to discussions on agent personality, self-healing systems and safe tooling, the program reflects the wide spectrum of risks and defenses that organizations must confront as AI agents take on more responsibility inside the enterprise.

Keynotes

• Johann Rehberger, Electronic Arts, Agentic ProbLLMs – Exploiting Coding Agents
• Steve Wilson, Exabeam, Agents as Insider Threats: Securing Against Your Fastest, Sneakiest Employees
• Michael Bargury, Zenity, Actually Making Progress in Security From AI

Sessions

• Jack Cable, Corridor, A Case Study of Vulnerabilities in AI Agents
• Ben Nassi, TAU / BlackHat, From Prompt Injection to Promptware: Evolution of Attacks Against LLM Applications
• David Campbell, Scale AI, Ignore Previous Instructions: Embracing AI Red Teaming
• Ken Huang, OWASP AIVSS, Risk Management in the Era of Agentic AI
• Jiquan Ngiam, MintMCP, X-Ray for Agents: Observability & Safe Tooling for MCP
• Allie Howe, Growth Cyber, Agentic Threats: From Theory to Practice

Lightning Talks

• Aderonke Akinbola, Google, Guardians of the Next Generation: Securing AI Agents in Child-Centric Ecosystems
• Vamsi Krishna Reddy Munnangi, Walmart, AI Agent Attack Vectors: Unveiling Self-Healing Vulnerabilities in Enterprise Systems
• Nate Lee, Trustmind, My AI is an INTJ: Understanding the Personality Traits of Your Autonomous Agents
• Kristen Beneduce, January, High Leverage Low Lift: What You Can Do Today to Secure AI
• Ryan Ray, Slalom, Securing Agentic AI: Threats, Models, and Mitigation in the Age of Autonomy
• Emile Delcourt, OWASP, Genetic Evolution in Adversarial Prompting: Subverting an AI Guard

Panels

• How Leading AI Platforms Approach Building Trustworthy Agents with ServiceNow, Google, and OpenAI
• The Why and How AIVSS Panel with Glean, Stanford University, OWASP, and Scale AI

“Agents now make real impacts in enterprise environments,” said Michael Bargury, co-founder and CTO of Zenity. “They handle sensitive data, access systems and make decisions at machine speed. This summit brings together the researchers uncovering vulnerabilities, the enterprises deploying agents, and the platforms building them so we can bridge the gap between innovation and security. Our goal is to facilitate practical conversations that will shape how organizations defend themselves. SecuringAI systems is a hard problem, and the only way to make meaningful progress is to come together as a community.”

Event Details

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

About Zenity

Zenity is the first security and governance platform purpose-built for AI agents - spanning SaaS, home grown platforms (Cloud), and end-user devices (Endpoint). Trusted by Fortune 500 enterprises, Zenity helps security teams confidently adopt AI by delivering defense in depth with full-lifecycle coverage: from agent discovery and posture management to real-time detection, inline prevention, and response. With an agent-centric approach that prioritizes how agents behave, what they access, and which tools they invoke, Zenity eliminates blind spots and enforces consistent policy and controls across environments so organizations can innovate with AI, without compromising security. Learn more at www.zenity.io

View source version on businesswire.com: https://www.businesswire.com/news/home/20250918300679/en/

This summit brings together the researchers uncovering vulnerabilities, the enterprises deploying agents, and the platforms building them so we can bridge the gap between innovation and security.