Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem
On the map: LLM safety and security → Prompt injection and agent security
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security. Builds on 1 of its 8 references that are in the map. First posted on arXiv 27 May 2026.
Builds on
1 of 8 references.
Closest ancestors · 1
Same direction, newest first
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
- 2026Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis
- 2026ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree
- 2026HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
- 2026MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
- 2026SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills
- 2026"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
- 2026Towards a Risk Assessment of Malicious Skill Files in Coding Agents