We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4% of all skills contain at least one critical-level security issue and at least 8 manually confirmed malicious skills remain publicly available on clawhub.ai as of the date of publication. This report documents our methodology, presents a threat taxonomy based on real-world samples, and details the attack patterns we observed. As skill marketplaces grow rapidly and AI agents gain access to sensitive credentials and systems, automated security analysis is no longer optional.
@article{arxiv.2605.28588,
title = {Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem},
author = {Luca Beurer-Kellner and Aleksei Kudrinskii and Marco Milanta and Kristian Bonde Nielsen and Hemang Sarkar and Liran Tal},
journal= {arXiv preprint arXiv:2605.28588},
year = {2026}
}