AI RESEARCH
A New Framework for Cybersecurity Refusals in AI Agents
arXiv CS.AI
•
ArXi:2606.02644v1 Announce Type: cross Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existing benchmarks for AI agents in cybersecurity focus mainly on measuring proficiency--how effectively agents can complete offensive security tasks--but neglect a critical question: when and how should agents refuse harmful requests? We present the first framework for establishing refusal boundaries in offensive security contexts.