Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916056114659328 |
|---|---|
| author | Beurer-Kellner, Luca Kudrinskii, Aleksei Milanta, Marco Nielsen, Kristian Bonde Sarkar, Hemang Tal, Liran |
| author_facet | Beurer-Kellner, Luca Kudrinskii, Aleksei Milanta, Marco Nielsen, Kristian Bonde Sarkar, Hemang Tal, Liran |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28588 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem Beurer-Kellner, Luca Kudrinskii, Aleksei Milanta, Marco Nielsen, Kristian Bonde Sarkar, Hemang Tal, Liran Cryptography and Security Artificial Intelligence 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. |
| title | Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2605.28588 |