SkillTester: Benchmarking Utility and Security of Agent Skills
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910087422935040 |
|---|---|
| author | Wang, Leye Wang, Zixing Xu, Anjie |
| author_facet | Wang, Leye Wang, Zixing Xu, Anjie |
| contents | 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 https://skilltester.ai, and the broader project is maintained at https://github.com/skilltester-ai/skilltester. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28815 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SkillTester: Benchmarking Utility and Security of Agent Skills Wang, Leye Wang, Zixing Xu, Anjie Cryptography and Security Artificial Intelligence 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 https://skilltester.ai, and the broader project is maintained at https://github.com/skilltester-ai/skilltester. |
| title | SkillTester: Benchmarking Utility and Security of Agent Skills |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2603.28815 |