AI Agent Security Masterclass

Code Blue 2025

AI Agent Security Masterclass

16 - 17 November, 2025

Tokyo

Abhay Bhargav

Key Take-Aways

How to architect and secure AI agents: sandboxing, strict permission models, prompt hardening, audit trails
Threat modelling specific to agent-based systems: prompt injection, data poisoning, malicious plugins etc.
Offensive security labs: hands-on red teaming for AI agents to understand how attackers exploit weaknesses
Understanding and using Model Context Protocol (MCP), secure tool orchestration and supply chain in agent frameworks
Practical code & framework exposure (Python), cloud labs; real exercises for both defense & offense

‍

Book a demo

More events that might interest you

6 November - 11 am EST

Inside the Mind of an AI Attacker

Walk away with the playbook to defend your own AI workflows using practical controls mapped to the OWASP Top 10 for LLMs and NIST AI RMF.

virtual

Learn More

9 Oct | 11 am EST

30 Minutes to Think Like an Attacker

See live how everyday data flows can lead to real vulnerabilities, and discover the frameworks, tools, and personal workflows that will help you level up your security skills.

Virtual

Learn More

Sep 18 - 11 AM EST

Danger in the Dependencies: Surviving supply chain attacks

This session takes you on a supply chain security thrill ride, zeroing in on malicious modules, hidden entry points, and the real tricks threat actors use to wreak havoc across the SDLC.

Virtual

Learn More

View all events