_(1).jpg)
Zenity has announced the full agenda for the AI Agent Security Summit 2025, set to take place on October 8 at the Commonwealth Club in San Francisco. The event will gather security experts, researchers, enterprise leaders, and major AI platforms to focus on one of the most pressing challenges in the enterprise technology landscape—securing AI agents. With keynotes, sessions, lightning talks, and panels, the program covers vulnerabilities, adversarial AI risks, enterprise adoption, and practical defenses, aiming to establish security best practices for the new era of intelligent agents.
Zenity announces full agenda for AI Agent Security Summit 2025 on Oct. 8 in San Francisco.
Featured speakers from Google, OpenAI, Walmart, EA, Exabeam, ServiceNow, Stanford, and more.
Agenda includes 3 keynotes, 6 sessions, 6 lightning talks, and 2 panels.
Topics cover coding agent vulnerabilities, insider threats, prompt injection, governance, and observability.
Event aims to bridge the gap between innovation and security for AI agents.
Registration available at zenity.io.
The one-day, multi-track summit features contributions shaped by over 100 submissions from the AI security community. With 3 keynotes, 6 sessions, 6 lightning talks, and 2 panels, the agenda examines risks associated with enterprise AI adoption and delivers real-world insight into defense strategies. Topics include AI red teaming, adversarial prompting, agent personality, risk management, observability, self-healing systems, and safe tooling.
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
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
Allie Howe (Growth Cyber): Agentic Threats: From Theory to Practice
Lightning talks by Google, Walmart, Slalom, OWASP, and others will cover cutting-edge issues such as AI agent vulnerabilities, self-healing systems, adversarial prompting, and agent personality analysis. Panels will examine trust and governance, with representatives from ServiceNow, OpenAI, Google, Glean, and Stanford.
“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.”
Date: October 8, 2025
Location: The Commonwealth Club, San Francisco, CA
Registration: zenity.io/resources/events/ai-agent-security-summit-2025
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 policies so organizations can innovate with AI without compromising security.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.