AI safety systems face a dual-use dilemma: the same request can be either harmless or harmful depending on who made it and why, which causes systems that make decisions based solely on the request's content to refuse legitimate queries and let pass harmful ones.To address this, we propose a conceptual access control framework, based on verified user credentials (such as institutional affiliation) and classifiers that assign model outputs to risk categories (such as advanced virology). The system permits responses only when the user's verified credentials match the category's requirements. For implementation of the model output classifiers, we introduce a theoretical approach utilizing small, gated expert modules integrated into the generator model, trained with gradient routing, that enable efficient risk detection without the capability gap problems of external monitors. While open questions remain about the verification mechanisms, risk categories, and the technical implementation, our framework makes the first step toward enabling granular governance of AI capabilities: verified users gain access to specialized knowledge without arbitrary restrictions, while adversaries are blocked from it. This contextual approach reconciles model utility with robust safety, addressing the dual-use dilemma.