Agentic Security: Lessons from Computer Architecture (opens in new tab)

When an agent makes an incorrect guess, the obvious mistakes like bad files or stale outputs are straightforward to see. However, there are less visible leaks that pose significant risks, such as timing patterns or cached context. The context and data exchanged between tools, services, and third-party systems can also be problematic. This situation becomes particularly concerning when AI agents take action before fully understanding the task at hand. This leads to an important question: Who h...