AgentHarm

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents Maksym Andriushchenko1,†,*, Alexandra Souly2,* Mateusz Dziemian1, Derek Duenas1, Maxwell Lin1, Justin Wang1, Dan Hendrycks1,§, Andy Zou1,¶,§, Zico Kolter1,¶, Matt Fredrikson1,¶,* Eric Winsor2, Jerome Wynne2, Yarin Gal2,♯, Xander Davies2,♯,* 1Gray Swan AI, 2

Papers using AgentHarm (2)

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning2026Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents2026