Jul 2026
OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills
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 safety risks that only emerge during actual execution. In this work, we conduct a systematic invest...
Qi-Yuan Liu, Tingfeng Hui, Kun Zhan et al.
· arXiv.org · 1 citation
· ⚡1