PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents

ArXi:2605.21694v1 Announce Type: cross Connecting large language models (LLMs) to defensive enforcement requires than asking a model whether an attack is happening. A defender must decide which model outputs may change the system state, which outputs must be rejected, and how failures should be recorded. We present PocketAgents, a manifest-driven library of autonomous defense agents. Each agent is installed as three data files: a manifest, a prompt, and a runtime context.