by protectskills · Claude Skill · ★ 68
"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills This repository contains a comprehensive security benchmark dataset and evaluation framework for Claude Code Agent Skills. The paper reports a three-tiered, nested dataset of 98,380 skills from two major platforms (skills.rest and skillsmp.com): 4,287 statically-flagged suspicious candidates (Tier 2), of which 157 are behaviorally-confirmed malicious skills (Tier 3).
| Stars | 68 |
| Forks | 6 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 60.1371893702931/100 |
| Last Updated | 2026-07-08 |
| Created | 2026-02-07 |
| Platforms | claude-code, python |
| Est. Tokens | ~17k |
Explore other popular claude skill tools:
MaliciousAgentSkillsBench is A Security Benchmark for Claude Code Agent Skills. It is categorized as a Claude Skill with 68 GitHub stars.
MaliciousAgentSkillsBench is primarily written in Python.
You can find installation instructions and usage details in the MaliciousAgentSkillsBench GitHub repository at github.com/protectskills/MaliciousAgentSkillsBench. The project has 68 stars and 6 forks, indicating an active community.
MaliciousAgentSkillsBench is released under the MIT license, making it free to use and modify according to the license terms.