Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem
This work highlights the emerging security threats in AI agent skill ecosystems, which is critical for developers and platform operators as agents gain access to sensitive systems.
Analysis of 3,984 AI agent skills from major marketplaces found 76 confirmed malicious payloads, with 13.4% of skills containing critical security issues and at least 8 malicious skills still publicly available.
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.