Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network…
安装
npx skills add alirezarezvani/claude-skills --skill skill-security-auditornpx skills add alirezarezvani/claude-skills --skill skill-security-auditor -a claude-code -gnpx skills add alirezarezvani/claude-skills --skill skill-security-auditor -a codex -ggemini skills install https://github.com/alirezarezvani/claude-skills.git --path engineering/skill-security-auditorgh skill install alirezarezvani/claude-skills skill-security-auditorgit clone --depth 1 https://github.com/alirezarezvani/claude-skills /tmp/alirezarezvani__claude-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/alirezarezvani__claude-skills/engineering/skill-security-auditor ~/.claude/skills/skill-security-auditor # Claude Code
cp -R /tmp/alirezarezvani__claude-skills/engineering/skill-security-auditor ~/.agents/skills/skill-security-auditor # Codex, Cursor, Gemini CLI, Copilot, OpenCode