MaliciousAgentSkillsBench

by protectskills · Claude Skill · ★ 68

About MaliciousAgentSkillsBench

"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).

Quick Facts

Stars68
Forks6
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score60.1371893702931/100
Last Updated2026-07-08
Created2026-02-07
Platformsclaude-code, python
Est. Tokens~17k

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is MaliciousAgentSkillsBench?

MaliciousAgentSkillsBench is A Security Benchmark for Claude Code Agent Skills. It is categorized as a Claude Skill with 68 GitHub stars.

What programming language is MaliciousAgentSkillsBench written in?

MaliciousAgentSkillsBench is primarily written in Python.

How do I install or use MaliciousAgentSkillsBench?

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.

What license does MaliciousAgentSkillsBench use?

MaliciousAgentSkillsBench is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse Claude Skill tools