Why Agents Get Compromised Through Tool Calls More Often Than Through the Conversation Itself

When AI Safety comes up, most people's intuitive image of an attack scenario is jailbreaking—a user in conversation trying every trick to induce the model into saying something it shouldn't. But as agent applications have become more widespread, the safety research community has gradually zeroed in on a more concerning pattern: attacks causing genuine real-world damage increasingly run through an agent's tool-calling path, rather than simple conversational inducement. This article covers the...