Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub

TL;DR

This paper provides an empirical analysis of ClawHub, a large public registry of LLM agent skills, revealing linguistic, functional, and security characteristics, and proposing a risk prediction benchmark.

Contribution

It offers the first systematic study of ClawHub's ecosystem, analyzing skill distribution, cross-lingual differences, and security risks, along with a new risk prediction benchmark.

Findings

English skills are more infrastructure-oriented, Chinese skills are scenario-driven.

Over 30% of skills are labeled suspicious or malicious.

A risk prediction model achieves 72.62% accuracy using submission-time signals.

Abstract

Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-driven capability sharing. However, despite their rapid growth, the functionality, ecosystem structure, and security risks of public skill registries remain underexplored. In this paper, we present an empirical study of ClawHub, a large public registry of agent skills. We build and normalize a dataset of 26,502 skills, and conduct a systematic analysis of their language distribution, functional organization, popularity, and security signals. Our clustering results show clear cross-lingual differences: English skills are more infrastructure-oriented and centered on technical capabilities such as APIs, automation, and memory, whereas Chinese skills are more application-oriented, with clearer scenario-driven clusters such as media generation, social content production, and finance-related services. We further find that more than 30% of all crawled skills are labeled as suspicious or malicious by available platform signals, while a substantial fraction of skills still lack complete safety observability. To study early risk assessment, we formulate submission-time skill risk prediction using only information available at publication time, and construct a balanced benchmark of 11,010 skills. Across 12 classifiers, the best Logistic Regression achieves a accuracy of 72.62% and an AUROC of 78.95%, with primary documentation emerging as the most informative submission-time signal. Our findings position public skill registries as both a key enabler of agent capability reuse and a new surface for ecosystem-scale security risk.