Position: AI Security Policy Should Target Systems, Not Models

ArXi:2605.09504v1 Announce Type: cross We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, parallel exploration, and evolutionary optimization. Together, our results nstrate that both safety bypass of frontier models and software vulnerability discovery, i.e., the capability class that motivated restricted release of Anthropic's Mythos Preview, are achievable at effectively zero cost using commodity hardware and openly available models. We report two experiments.