SkillVetBench

SkillVetBench is a two-stage security vetting benchmark designed to evaluate the detection of malicious skills and the verification of their runtime behavior in open agentic skill ecosystems.

Papers using SkillVetBench (2)

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems2026SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills2026