Use when building autonomous LLM agents operating in live environments. Protects against prompt injection, tool abuse, data exfiltration, and runaway loops. Keywords: guardrails, prompt injection, IPI, safety, sandboxing, NeMo, LLM Guard.
安装
npx skills add VoDaiLocz/kilo-kit-mcp --skill ai-guardrailsnpx skills add VoDaiLocz/kilo-kit-mcp --skill ai-guardrails -a claude-code -gnpx skills add VoDaiLocz/kilo-kit-mcp --skill ai-guardrails -a codex -ggemini skills install https://github.com/VoDaiLocz/kilo-kit-mcp.git --path skills/security/ai-guardrailsgh skill install VoDaiLocz/kilo-kit-mcp ai-guardrailsgit clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcp /tmp/VoDaiLocz__kilo-kit-mcp
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/VoDaiLocz__kilo-kit-mcp/skills/security/ai-guardrails ~/.claude/skills/ai-guardrails # Claude Code
cp -R /tmp/VoDaiLocz__kilo-kit-mcp/skills/security/ai-guardrails ~/.agents/skills/ai-guardrails # Codex, Cursor, Gemini CLI, Copilot, OpenCode