SkillTester: Benchmarking Utility and Security of Agent Skills
Published in arXiv:2603.28815, 2026
An agent-driven benchmark system for evaluating the utility and security of agent skills through paired baseline/with-skill execution and dedicated security probes.
Recommended citation: Leye Wang, Zixing Wang, and Anjie Xu. (2026). "SkillTester: Benchmarking Utility and Security of Agent Skills." arXiv:2603.28815.
Download Paper
