Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively similar. A practical screen must catch nearly every attack while keeping the review load manageable. We present SkillScreen, a compact decision model trained to...
Jerrold Huang, Jun-Wei Quan, Saiyue Lyu et al.· 2 citations
This work introduces SkillTV-Bench, a 681-case benchmark of real agent trajectories from 50 tasks across eleven domains, designed to evaluate skill-aware trajectory verification for both LLM-as-a-Judge and Agent-as-a-Judge methods, and proposes SkillTV-Evolve, which externalizes verification knowledge as a reusable Jud...
Zhien Han, C. Zeng, Liuhaichen Yang et al.· 0 citations
Skill2Query is a framework that first parses a skill document into a Skill Knowledge Graph and then generates pseudo-queries through a three-stage process including style mimicking, query template generation, and parameter filling, which consistently improves sparse, dense, and skill-routing retrieval.
Lihui Ding, Zi-Han Guo, Bingwei Lu et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.