Session 2 of 7 The session outlines a fictional case study involving “Finbot,” an AI finance assistant that was manipulated through prompt injection attacks, leading to fraudulent payments and data breaches. The presentation highlights how attackers poisoned Finbot’s memory, manipulated tools to execute unauthorized actions, and exploited identity misconfigurations to escalate privileges. It underscores the […]

Session 1 of 7 The introductory session for the Agentic Workshop outlines the objectives and structure of the Agentic Security Initiative (ASI), emphasizing the importance of community engagement and practical application. Led by project co-leads, the session introduces the initiative’s focus on identifying agentic AI threats, developing security guidelines, and providing practical tools for threat