Skip to content
Skill

Implementing LLM guardrails for security

Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content gene

Install
Scripts
None
Platforms
Claude Code, Codex, Cursor
GitHub stars
72
Last commit
18 days ago
License
Apache-2.0
Listing updated
today

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.

From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.

What it can access

From a static check of its 1 file (9 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.

Install

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

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

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

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.

Claude Code docs on skills

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

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.

Codex docs on skills

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

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.

Cursor docs on skills

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

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.

Gemini CLI docs on skills

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

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.

VS Code docs on skills

Get the folder:

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.

The SKILL.md format

Implementing LLM guardrails for security 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.

More from plurigrid/asi

  1. Org-agenda-like transient views for ASI skill orchestration via nbb/squint + Emacs hydra

    • Open source
    • 72 GitHub stars
  2. Connect and stream from OpenBCI Cyton/Daisy via USB dongle, including first-time radio channel pairing

    • Open source
    • 72 GitHub stars
  3. Hypothesis-Test Loops via REPL for Exploratory Abductive Inference with Gay.jl colors

    • Open source
    • 72 GitHub stars
  4. Layer 4 Learning and Pattern Extraction for Cognitive Surrogate Systems

    • Open source
    • 72 GitHub stars
  5. Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration

    • Open source
    • 72 GitHub stars
  6. Automated code review for pull requests using specialized review patterns

    • Open source
    • 72 GitHub stars
    • Developer tools

Alternatives to Implementing LLM guardrails for security

  1. Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design

    • 196K GitHub stars
    • AI models and LLM tooling
  2. Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching cour

    • 196K GitHub stars
    • AI models and LLM tooling
  3. Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model

    • 196K GitHub stars
    • AI models and LLM tooling
  4. Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  5. Comprehensive guide for configuring and managing GitHub Dependabot

    • Open source
    • 41.3K GitHub stars
    • Security
  6. Build Model Context Protocol (MCP) servers in C#/.NET against the current ModelContextProtocol 2.x NuGet packages

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling