ClawHub

Emerging

1papers using it

2026first seen

ClawHub is a dataset/benchmark that contains a dual-view of LLM-generated reviews alongside official marketplace verdicts, used to evaluate the security and risk of community-contributed skills in open-source LLM agent ecosystems.

🔎 Find this dataset

Papers using ClawHub (1)

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills2026