No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by pashov · Agent Tool · ★ 1.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is skills safe to install? View the security audit →
Pashov Audit Group Skills AI-powered Solidity security skills — built by Pashov Audit Group. Supported AI Platforms: [. High-quality image, video
471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the cc
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, sl
Universal Claude Code workflow plugin with agents, skills, hooks, and commands
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-cal
Explore other popular agent tool tools:
skills is Pashov Audit Group Skills. It is categorized as a Agent Tool with 1.2k GitHub stars.
skills is primarily written in JavaScript. It covers topics such as agent-skills, ai-agents, ai-security.
You can find installation instructions and usage details in the skills GitHub repository at github.com/pashov/skills. The project has 1.2k stars and 225 forks, indicating an active community.
skills is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to skills on Agent Skills Hub include agent-skills-hub, Generative-Media-Skills, claude-code-plugins-plus-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: