Deploys Llama Guard 3 safety classification, NeMo Guardrails programmable dialogue rails, and LLM Guard input/output scanner pipelines as complementary runtime defenses that inspect and constrain LLM prompts and responses.
安装
npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill defending-llms-with-guardrailsnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill defending-llms-with-guardrails -a claude-code -gnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill defending-llms-with-guardrails -a codex -ggemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/defending-llms-with-guardrailsgh skill install mukul975/Anthropic-Cybersecurity-Skills defending-llms-with-guardrailsgit clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills /tmp/mukul975__Anthropic-Cybersecurity-Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/mukul975__Anthropic-Cybersecurity-Skills/skills/defending-llms-with-guardrails ~/.claude/skills/defending-llms-with-guardrails # Claude Code
cp -R /tmp/mukul975__Anthropic-Cybersecurity-Skills/skills/defending-llms-with-guardrails ~/.agents/skills/defending-llms-with-guardrails # Codex, Cursor, Gemini CLI, Copilot, OpenCode