Defending Llms with Guardrails

Deploy Llama Guard, NeMo Guardrails, and LLM Guard input/output scanners as runtime defenses.

100 stars 27 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add adriannoes/awesome-agentic-ai --skill defending-llms-with-guardrails
Manual install
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai.git /tmp/awesome-agentic-ai
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-agentic-ai/cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/defending-llms-with-guardrails ~/.claude/skills/defending-llms-with-guardrails

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Defending LLMs with Guardrails

> **Defensive scope:** This skill describes runtime defenses for production LLM applications. The example jailbreak/injection payloads exist only to validate that guardrails block them. Test against systems you own or are authorized to assess.

## Overview

Large language model (LLM) applications are exposed to adversarial input (jailbreaks, prompt injection, toxic content) and can emit unsafe, biased, or sensitive output. A guardrail is a runtime control that inspects and constrains the data flowing into and out of an LLM. Three production-grade, open-source guardrail systems dominate the ecosystem and are complementary rather than mutually exclusive:

- **Llama Guard 3** (Meta) — a Llama-3.1-8B model fine-tuned as a *safety classifier*. Given a prompt or a response, it emits `safe` or `unsafe` plus the violated MLCommons hazard categories (S1–S14). It is the strongest *semantic* content-safety classifier of the three and supports prompt classification, response classification, and tool-call/code-interpreter classification across 8 languages.
- **NeMo Guardrails** (NVIDIA) — a *programmable* dialogue-rail framework. You define `input`, `output`, `dialog`, `retrieval`, and `execution` rails in a `config.yml` plus Colang (`.co`) flows. It can call external models (including Llama Guard) as actions, enforce topical boundaries, and add fact-checking/jailbreak-detection rails.
Read the full skill on GitHub

Details

Skill name
defending-llms-with-guardrails
Path
cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/defending-llms-with-guardrails/SKILL.md
License
MIT
Repo updated
2 November 2026

FAQ

What does the Defending Llms with Guardrails skill do?

Deploy Llama Guard, NeMo Guardrails, and LLM Guard input/output scanners as runtime defenses.

How do I install the Defending Llms with Guardrails skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add adriannoes/awesome-agentic-ai --skill defending-llms-with-guardrails. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Defending Llms with Guardrails popular?

It lives in adriannoes/awesome-agentic-ai, which has 100 GitHub stars and 27 forks, and is included in 2 curated skill lists.

Related skills

Browserstack

100

adriannoes/awesome-agentic-ai

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".

Testing & QAIn 2 lists27

Coverage

100

adriannoes/awesome-agentic-ai

Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".

Testing & QAIn 2 lists27

Fix

100

adriannoes/awesome-agentic-ai

Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".

Testing & QAIn 2 lists27

Delegating to Agents

100

adriannoes/awesome-agentic-ai

How to delegate work to another AI agent (Pi, Codex, Claude Code, Hermes) — picking the right agent, sending prompts to TUI agents, polling progress. Read BEFORE any `cmux send`/`tmux send-keys` to an agent, or whenever delegating, relaying, spawning, or orchestrating agent-to-agent work.

AI, LLMs & AgentsIn 2 lists27

Continuous LLM Red Teaming with Promptfoo

100

adriannoes/awesome-agentic-ai

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

AI, LLMs & AgentsIn 2 lists27

Detecting AI Model Prompt Injection Attacks

100

adriannoes/awesome-agentic-ai

Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison''s promp

AI, LLMs & AgentsIn 2 lists27

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.