skills.rest
choice5346
choice5346COMMUNITY
Explore all skills by this author →
GitHub

nemo-guardrails

Implements NVIDIA's NeMo Guardrails for runtime LLM application safety using programmable rails in the CoLang DSL.

Updated Aug 23, 2026
Search Tags:#hallucination detection#prompt injection#guardrails#pii filtering#llm security#safety alignment
One-click install
npx skills add https://github.com/choice5346/BiSHE --skill nemo-guardrails-choice5346
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nemo-guardrails
Source: https://github.com/choice5346/BiSHE/tree/main/.github/skills/nemo-guardrails
Command: npx skills add https://github.com/choice5346/BiSHE --skill nemo-guardrails-choice5346

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a robust framework for adding programmable safety, security, and reliability to LLM applications at runtime, preventing harmful outputs and ensuring factual accuracy.

Core Features & Use Cases

  • Runtime Safety: Implements guardrails to detect and block jailbreaks, prompt injections, and toxic content.
  • Input/Output Validation: Ensures user inputs and LLM outputs adhere to defined policies.
  • Fact-Checking & Hallucination Detection: Verifies factual claims made by the LLM.
  • PII Filtering: Masks or removes Personally Identifiable Information.
  • Use Case: Protect a customer-facing chatbot from generating inappropriate responses, ensuring it never reveals sensitive information or engages in harmful dialogue.

Quick Start

Install the library and use the provided Python code to define safety rules for your LLM application.

Frequently Asked Questions about nemo-guardrails

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add guardrails to an LLM application to prevent prompt injection and jailbreaking?▼

You add guardrails to an LLM application by implementing programmable runtime safety rails using Colang 2.0 DSL, which detects and blocks jailbreaks, prompt injections, and toxic content before they reach the model.

What is the best way to filter PII and detect hallucinations in chatbot outputs?▼

The best way to filter PII and detect hallucinations is to use a runtime safety framework that integrates tools like Presidio for PII filtering and LlamaGuard for security, verifying factual claims and masking sensitive information.

How does Colang 2.0 work for programming LLM safety alignment and input validation?▼

Colang 2.0 works as a DSL for programming LLM safety alignment by defining programmable rails that enforce input and output validation, ensuring user inputs and LLM outputs adhere strictly to defined security policies.

Can I use NeMo Guardrails to secure a customer-facing chatbot at runtime?▼

Yes, you can use NeMo Guardrails to secure a customer-facing chatbot at runtime, protecting it from generating inappropriate responses, preventing harmful dialogue, and ensuring it never reveals sensitive information.

Do I need external dependencies to implement LLM security and toxicity filtering?▼

You do not need mandatory external dependencies to implement basic LLM security and toxicity filtering, though integrating specialized tools like Presidio and LlamaGuard enhances PII filtering and safety alignment capabilities.

Related Skills

Explore More Software Engineering Skills→
handsomelong922handsomelong922

nemo-guardrails

Enforce runtime safety policies for LLM applications with configurable rails.

Community
Advanced
masermediagroup-stackmasermediagroup-stack
1

evaluating-llms

Evaluate LLM systems with automated metrics, LLM-as-judge rubrics, and standardized benchmarks.

Community
Advanced
MesferAliMesferAli

nemo-guardrails

Implement NeMo Guardrails with Colang 2.0 for LLM safety and security.

Community
Advanced
RazisafirRazisafir
1

implementing-llm-guardrails-for-security

Validate LLM inputs and outputs with NeMo Guardrails and Python validators.

Community
Advanced