skillguard
CommunitySecurity audit for AI skills before installation.
Authormpelissari
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Identifies security risks in AgentSkill packages before installation, helping teams avoid deploying unsafe skills.
Core Features & Use Cases
- Multi-layer analysis combining fast pattern scanning, AST/evasion checks, and prompt-injection analysis to detect credential theft, code injection, prompt manipulation, data exfiltration, and evasion techniques.
- Context-aware scoring that reduces false positives and highlights actionable risk signals tailored to the skill's declared capabilities.
- Seamless ClawHub integration to scan local and registry-sourced skills with consistent risk reporting.
Quick Start
Place SkillGuard in your tooling and run a local skill scan to audit before installation.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: skillguard Download link: https://github.com/mpelissari/openclaw-backup/archive/main.zip#skillguard Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.