paper-with-me

Papers

SkillTester: Benchmarking Utility and Security of Agent Skills

2026-03-28 · Leye Wang, Zixing Wang, Anjie Xu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.28815

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

2026-04-06 · Yujian Liu, Jiabao Ji, Li An, Tommi Jaakkola 외 arxiv

Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benc…

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills

2026-05-13 · Haomin Zhuang, Hanwen Xing, Yujun Zhou, Yuchen Ma 외 arxiv

Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills…

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems

2026-05-30 · Ismail Hossain, Sai Puppala, Zhuoran Lu, Sajedul Talukder 외 arxiv

Open agent platforms allow community contributors to publish reusable skills that agents can invoke at runtime. This extensibility also creates a supply-chain risk: malicious contributors can hide harmful behavior inside…

SkillAudit: From Fixed-Suite Benchmarking to Skill-Centered Assessment

2026-06-21 · Dexu Yu, Youhua Li, Zhaoyang Guan, Xianhao Lin 외 arxiv

Agent skills have become a practical way to extend large language model agents, but the growing skill ecosystem still lacks a reliable way to judge whether a skill is worth deploying. Existing evaluation methods remain l…

OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills

2026-07-22 · Qiyuan Liu, Tingfeng Hui, Kun Zhan, Kaike Zhang 외 arxiv

LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seemingly harmless skills can contain latent…