AI Agents Gone Rogue? Build, Defend & Attack AI-Enabled Apps • Katie Paxton-Fear • YOW! 2025

Why watch

Katie Paxton-Fear explores the emerging security risks of AI agents in this YOW! 2025 conference talk, covering real-world vulnerabilities including prompt injection, framework exploits, and the concept of hackbots. Ideal for security professionals, developers, and anyone building AI-enabled applications who wants to understand the attack surface before deploying agents.