# LLM safety guardrails (/ai--guardrails)

/ai--guardrails is a Claude Code skill in the AI & Agents section. Adds input and output filters, prompt-injection defense and personal-data handling around an AI feature, then proves them with adversarial tests.

- Web version: https://skills.sgomez.dev/en/s/ai--guardrails
- Section: [AI & Agents](https://skills.sgomez.dev/en/ai.md)
- Author: Santiago Gómez de la Torre
- License: MIT
- Source: https://github.com/sgomez-dev/claude-skills/blob/main/skills/ai/guardrails.md
- Updated 10 Jul 2026

## How to ask for it

- `/ai--guardrails protect my chatbot from prompt injection`
- `/ai--guardrails filter PII before it reaches the model`
- `/ai--guardrails run jailbreak tests against my assistant`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```

Claude Code plugin:

```
/plugin marketplace add sgomez-dev/claude-skills
/plugin install ai-skills@claude-skills-collection
```

## Permissions

- Reads: `**/*`
- Writes: `**/*`
- Runs: `project test/eval runners`
- Network: No
- Destructive: No

## Author's description

LLM guardrails - input/output filters, injection defense, PII, jailbreak tests

## Pairs well with

- [Production chatbot scaffold (/ai--chatbot-scaffold)](https://skills.sgomez.dev/en/s/ai--chatbot-scaffold.md): Scaffolds a chatbot on your existing stack: streaming responses, persistent conversation history, optional RAG grounding and a feedback loop.
- [Embeddings and semantic search (/ai--embeddings)](https://skills.sgomez.dev/en/s/ai--embeddings.md): Implements vector embeddings in your app for semantic search, RAG or similarity matching: ingestion, chunking, querying and relevance tuning.
- [RAG pipeline evaluation (/ai--rag-eval)](https://skills.sgomez.dev/en/s/ai--rag-eval.md): Builds a test harness that measures a RAG pipeline: a golden question set, retrieval metrics, groundedness checks and a regression gate.
- Recipe: [/pipeline--llm-app](https://github.com/sgomez-dev/claude-skills/blob/main/pipelines/llm-app.yaml): LLM App

- [How we review this](https://skills.sgomez.dev/en/methodology.md)