Agent skill · security · aradotso
skill-security-scanner
Claude Skills security scanning tool that detects malicious code, network requests, file access, and command injection risks before installation
Why this skill is useful
Adds executable security scanning capabilities for detecting malicious code and vulnerabilities in Claude Skills that the AI cannot generate on its own.
What it needs
Requires git, pip, pyinstaller installed locally. About 7k tokens when loaded. Last updated 2026-08-04. 11 stars on the source repository.
What this skill does
Skill Security Scanner Skill by ara.so — Security Skills collection. Overview skill-security-scanner is a command-line security analysis tool specifically designed to scan Claude Skills for malicious code, unauthorized network requests, sensitive file access, command injection, and other security risks. It performs static analysis without executing code, providing risk scores, detailed reports in multiple formats (HTML, JSON, console), and supports both English and Chinese interfaces. Key capabilities: Multi-dimensional security detection (network, file, command, code injection) Intelligent risk scoring (CRITICAL/WARNING/INFO) Multiple output formats (HTML reports with visualizations, JSON, colored console) Customizable rules and whitelisting Automatic scanning of .claude/skills/ directory Internationalization support (zhCN, enUS) Installation For standalone executable (no Python required): Core Commands Basic Scanning Report Generation Advanced Options Security Detection Rules CRITICAL Severity Rules NET001 - External Network Requests FILE001 - Sensitive File Access FILE002 - Dangerous File Operations CMD001 - Dangerous System Commands INJ001 - Code Injection Patterns INJ003 - Backdoor Implantation WARNING Severity Rules CMD002 - System Command Execution INJ002 - Dynamic Code Execution DEP001 - Global Package Installation Whitelisted Domains Configuration Custom Rules File Create custom-rules.yaml: Use custom rules: Whitelist Management Real-World Usage Examples Example 1: Pre-Installation Security Check Example 2: CI/CD Integration Example 3: Bulk Skill Auditing Example 4: Custom Rule for Specific Threat Interpreting Scan Results Risk Score Calculation HTML Report Features Dashboard: Visual risk meter, issue distribution chart Filterable Issues: Click severity badges to filter File Navigation: Jump to specific files and line numbers Confidence Levels: High/Medium/Low pattern match confidence Recommendations: Automated suggestions based on findings Console Output E …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/skill-security-scanner