Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
skill-security-scan
skill-security-scan is a command-line tool designed to scan and detect security risks in Claude Skills. Before installing third-party Skills, use this tool for security review to effectively prevent malicious code from stealing data or compromising your system.
145stars
11forks
Python
claude-codeskills
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
CLI tool that scans Claude Skills for security risks like file access, network calls, and command execution before installation.
Use this when
- Reviewing a new Skill before installing it
- Checking Skills in a shared development environment
- Auditing Skills for sensitive data exposure risks
- Verifying Skills don't make unexpected network requests
- Ensuring Skills don't execute dangerous system commands
Don't use when
- Scanning non-Skill Python projects
- Checking Skills already installed and running
- Testing Skills in production environments
Capabilities
- Detects file system access to sensitive paths (SSH keys, .env)
- Identifies network requests to non-whitelisted domains
- Flags dangerous command executions (rm, sudo, chmod)
- Generates HTML, JSON, or console security reports
- Supports custom rule configuration for project needs
- Scans both Skills directory and project paths automatically
InstallSKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest huifer/skill-security-scanAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/skill-security-scan curl -fsSL https://raw.githubusercontent.com/huifer/skill-security-scan/main/SKILL.md -o ~/.claude/skills/skill-security-scan/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
skill-security-scan — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt