Heuristic security scan of installed skills — prompt-injection phrases, hidden unicode instructions, credential-store access, network-pipe-to-shell and payload-smuggling patterns. Use when the user asks 'are my skills safe', wants to scan skills for prompt injection or malware patterns, or before trusting a newly installed skill. Trigger with '/janitor-security'.
安装
npx skills add khendzel/skills-janitor --skill janitor-securitynpx skills add khendzel/skills-janitor --skill janitor-security -a claude-code -gnpx skills add khendzel/skills-janitor --skill janitor-security -a codex -ggemini skills install https://github.com/khendzel/skills-janitor.git --path skills/janitor-securitygh skill install khendzel/skills-janitor janitor-securitygit clone --depth 1 https://github.com/khendzel/skills-janitor /tmp/khendzel__skills-janitor
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/khendzel__skills-janitor/skills/janitor-security ~/.claude/skills/janitor-security # Claude Code
cp -R /tmp/khendzel__skills-janitor/skills/janitor-security ~/.agents/skills/janitor-security # Codex, Cursor, Gemini CLI, Copilot, OpenCode