skill-scanner

🥈Silver

Skill Scanner is a security tool for validating agent skills. It benefits operations teams by ensuring agent skills are secure before deployment. It integrates with Claude agents and is applied during the skill development and testing phases.

72120Updated 1mo ago

Intermediate30min to implementautomation

Saves ~300 min per use

Quick InstallView Source

git clone https://github.com/cisco-ai-defense/skill-scanner.git

Works with:

Claude

Overview

About This Skill

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/cisco-ai-defense/skill-scanner

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Scan the following AI skill for potential security vulnerabilities: [SKILL_NAME]. Look for issues like data leakage, unauthorized access, or malicious code execution. Provide a detailed report with findings and recommendations.

Example Output

# Security Scan Report for 'Data Analyzer' Skill

## Findings
- **Data Leakage Risk**: The skill may inadvertently expose sensitive data from [COMPANY] when processing [INDUSTRY] datasets.
- **Access Control**: No explicit access control mechanisms are implemented for [DATA] handling.
- **Input Validation**: Lack of input validation could lead to injection attacks.

## Recommendations
- Implement data anonymization for sensitive information.
- Add role-based access control for [DATA] access.
- Validate and sanitize all user inputs.
- Regularly audit the skill's data handling processes.