SkillTester: Benchmarking Utility and Security of Agent Skills

Computer Science > Cryptography and Security [Submitted on 28 Mar 2026] SkillTester: Benchmarking Utility and Security of Agent Skills Leye Wang, Zixing Wang, Anjie Xu This technical report presents SkillTester, a tool for evaluating the utility and security of agent skills. Its evaluation framework combines paired baseline and with-skill execution conditions with a separate security probe suite. Grounded in a comparative utility principle and a user-facing simplicity principle, the framework normalizes raw execution artifacts into a utility score, a security score, and a three-level security status label. More broadly, it can be understood as a comparative quality-assurance harness for agent skills in an agent-first world. The public service is deployed at this https URL, and the broader project is maintained at this https URL. Comments: Technical report, 13 pages, 2 figures, 9 tables. Project page: this https URL. Code: this https URL Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.28815 [cs.CR]   (or arXiv:2603.28815v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.28815 Focus to learn more Submission history From: Leye Wang [view email] [v1] Sat, 28 Mar 2026 14:56:18 UTC (257 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)