skill-guard

Official

Runtime security monitor for skills.

AuthorUseAI-pro
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill acts as a vigilant guardian, monitoring active OpenClaw skills in real-time to detect and flag any behavior that deviates from their declared permissions or exhibits suspicious patterns, thereby preventing potential security breaches or unintended actions.

Core Features & Use Cases

  • Runtime Monitoring: Observes file access, network calls, and shell commands executed by active skills.
  • Anomaly Detection: Identifies unusual behavior, such as accessing credential files or making unexpected network connections.
  • Permission Enforcement: Flags any actions that violate the permissions explicitly declared in the skill's SKILL.md.
  • Use Case: When a code generation skill unexpectedly starts attempting to write to system configuration files or make outbound network requests to unknown servers, Skill Guard will immediately detect and alert on this suspicious activity.

Quick Start

Monitor the active skill 'data-processor' for any file access, network calls, or shell commands that violate its declared permissions.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: skill-guard
Download link: https://github.com/UseAI-pro/openclaw-skills-security/archive/main.zip#skill-guard

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.