# Implementing LLM guardrails for security

> Implementing LLM guardrails for security is an open-source agent skill for security. Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content gene. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/plurigrid/asi/tree/main/plugins/asi/skills/implementing-llm-guardrails-for-security
- **Repository:** https://github.com/plurigrid/asi
- **GitHub stars:** 72
- **License:** Apache-2.0
- **Skill name:** implementing-llm-guardrails-for-security
- **Collection:** https://github.com/plurigrid/asi
- **Categories:** security, AI models and LLM tooling
- **Listing updated:** 2026-11-17

## About

Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content policy enforcement, and the Guardrails AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts, stripping PII, enforcing topic boundaries) and model outputs (detecting hallucinations, filtering toxic content, validating JSON schema compliance). Activates for requests involving LLM output validation, AI content filtering, guardrail implementation, or LLM safety enforcement.

## When your agent uses it

> Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content policy enforcement, and the Guardrails AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts, stripping PII, enforcing topic boundaries) and model outputs (detecting hallucinations, filtering toxic content, validating JSON schema compliance). Activates for requests involving LLM output validation, AI content filtering, guardrail implementation, or LLM safety enforcement.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/plurigrid/asi/tree/HEAD/plugins/asi/skills/implementing-llm-guardrails-for-security)
- [License: Apache-2.0](https://github.com/plurigrid/asi/tree/HEAD/plugins/asi/skills/implementing-llm-guardrails-for-security)

## Install

### Claude Code

This skill ships in the `asi` plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):

```sh
/plugin marketplace add plurigrid/asi
/plugin install asi@asi
```

Or copy only this skill to `~/.claude/skills/implementing-llm-guardrails-for-security`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/implementing-llm-guardrails-for-security &&
cp -R "$tmp/plugins/asi/skills/implementing-llm-guardrails-for-security" ~/.claude/skills/implementing-llm-guardrails-for-security &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/implementing-llm-guardrails-for-security` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/implementing-llm-guardrails-for-security` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/implementing-llm-guardrails-for-security &&
cp -R "$tmp/plugins/asi/skills/implementing-llm-guardrails-for-security" ~/.agents/skills/implementing-llm-guardrails-for-security &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/implementing-llm-guardrails-for-security` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/implementing-llm-guardrails-for-security` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/implementing-llm-guardrails-for-security &&
cp -R "$tmp/plugins/asi/skills/implementing-llm-guardrails-for-security" ~/.cursor/skills/implementing-llm-guardrails-for-security &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/implementing-llm-guardrails-for-security` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/plurigrid/asi.git --path plugins/asi/skills/implementing-llm-guardrails-for-security
```

Or copy the folder to `~/.gemini/skills/implementing-llm-guardrails-for-security` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/implementing-llm-guardrails-for-security`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/plurigrid/asi.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/implementing-llm-guardrails-for-security &&
cp -R "$tmp/plugins/asi/skills/implementing-llm-guardrails-for-security" ~/.copilot/skills/implementing-llm-guardrails-for-security &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/implementing-llm-guardrails-for-security` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/plurigrid/asi.git
```

Then copy `asi/plugins/asi/skills/implementing-llm-guardrails-for-security` into your agent's skills folder as `implementing-llm-guardrails-for-security`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Implementing LLM guardrails for security in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/implementing-llm-guardrails-for-security to use it in all your projects, or to .claude/skills/implementing-llm-guardrails-for-security in one project. Or install the asi plugin, which includes it: /plugin marketplace add plurigrid/asi, then /plugin install asi@asi.

### Does Implementing LLM guardrails for security run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Implementing LLM guardrails for security?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to Implementing LLM guardrails for security?

The closest alternatives to Implementing LLM guardrails for security are MCP builder, Academy guide, Claude API, Arize AI provider integration and Dependabot.

## Alternatives

- [MCP builder](https://ai-powered.com/skills/mcp-builder): MCP builder is an agent skill for ai models and llm tooling.
- [Academy guide](https://ai-powered.com/skills/academy-guide): Academy guide is an agent skill for ai models and llm tooling.
- [Claude API](https://ai-powered.com/skills/claude-api): Claude API is an agent skill for ai models and llm tooling.
- [Arize AI provider integration](https://ai-powered.com/skills/arize-ai-provider-integration): Arize AI provider integration is an open-source agent skill for ai models and llm tooling.
- [Dependabot](https://ai-powered.com/skills/dependabot): Dependabot is an open-source agent skill for security.
- [Dotnet MCP builder](https://ai-powered.com/skills/dotnet-mcp-builder): Dotnet MCP builder is an open-source agent skill for ai models and llm tooling.
- [Update llms](https://ai-powered.com/skills/update-llms): Update llms is an open-source agent skill for ai models and llm tooling.
- [Phoenix evals](https://ai-powered.com/skills/phoenix-evals): Phoenix evals is an open-source agent skill for ai models and llm tooling.

---
Source: https://ai-powered.com/skills/implementing-llm-guardrails-for-security
