Scan agent skills for security issues. Use when asked to "scan a skill", "audit a skill", "review skill security", "check skill for injection", "validate SKILL.md", or assess whether an agent skill is safe to install. Checks for prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.
安装
npx skills add getsentry/skills --skill skill-scannernpx skills add getsentry/skills --skill skill-scanner -a claude-code -gnpx skills add getsentry/skills --skill skill-scanner -a codex -ggemini skills install https://github.com/getsentry/skills.git --path skills/skill-scannergh skill install getsentry/skills skill-scannergit clone --depth 1 https://github.com/getsentry/skills /tmp/getsentry__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/getsentry__skills/skills/skill-scanner ~/.claude/skills/skill-scanner # Claude Code
cp -R /tmp/getsentry__skills/skills/skill-scanner ~/.agents/skills/skill-scanner # Codex, Cursor, Gemini CLI, Copilot, OpenCode