AI agents introduce an array of threats to companies distinct from those arising with traditional software. In multiple ways, agents expand the attack surface that organizations must defend. This article, the second in a two-part series on real-world security for AI agents, provides an action plan for CISOs and lawyers to strengthen security and reduce risks around AI agents, with expert perspectives from agent security specialists at Barndoor, Gravitee, Gray Swan, Skyflow and ZwillGen. Part one discussed corporate benchmarks revealed in three reports on actual incidents involving agents, and the safeguards and security measures that companies have begun to apply to agents. See “Restricting Super Users and Zombie IDs to Increase Cloud Security” (Jul. 31, 2024).