Session 6 of 7

The session focused on secure agentic applications, led by experts from AWS, Intuit, and Pangea. It outlined a methodology for identifying threats in agentic AI systems, emphasizing development lifecycle stages, key components, architectures, and operational environments.

The discussion highlighted key threats such as memory poisoning, tool misuse, and identity spoofing in single and multi-agent architectures, including peer-to-peer setups. Mitigation strategies included implementing guardrails, refining prompts, using centralized and decentralized trust mechanisms, and ensuring robust identity management. Participants