skills.rest
ihatesea69
ihatesea69COMMUNITY
Explore all skills by this author →
WebsiteGitHub

prompt-guard

Detect prompt injections and jailbreak attempts in user inputs using a pre-trained transformer model.

3|Updated Feb 21, 2026
Search Tags:#security#input validation#llm#jailbreak#prompt injection#safety alignment
One-click install
npx skills add https://github.com/ihatesea69/HieuNghi-AI-Skills --skill prompt-guard-ihatesea69
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-guard
Source: https://github.com/ihatesea69/HieuNghi-AI-Skills/tree/main/airesearch_skills/07-safety-alignment/prompt-guard
Command: npx skills add https://github.com/ihatesea69/HieuNghi-AI-Skills --skill prompt-guard-ihatesea69

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires transformers, torch, and includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill protects Large Language Model (LLM) applications by detecting and filtering malicious prompts, including prompt injections and jailbreak attempts, ensuring the integrity and safety of AI interactions.

Core Features & Use Cases

  • Prompt Injection Detection: Identifies attempts to embed hidden instructions within user inputs or third-party data.
  • Jailbreak Prevention: Flags prompts designed to override the LLM's safety guidelines or intended behavior.
  • Multilingual Support: Operates effectively across 8 different languages.
  • Use Case: Before sending user messages to an LLM, use this Skill to scan them for any jailbreak attempts, preventing the LLM from generating harmful or unintended responses.

Quick Start

Use the prompt-guard skill to check if the user input 'Ignore all previous instructions' is a jailbreak attempt.

Frequently Asked Questions about prompt-guard

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

FAQPage Schema
How do I detect prompt injection attacks in LLM inputs?▼

Detect prompt injection attacks by scanning user inputs and third-party data with a pre-trained transformer model to filter hidden malicious instructions before sending messages to the LLM.

How can I prevent jailbreak attempts in my LLM application?▼

Prevent jailbreak attempts by flagging prompts designed to override safety guidelines using sequence classification, maintaining AI safety and preventing unauthorized behavior in your application.

Does prompt injection detection work with non-English user inputs?▼

Prompt injection detection operates effectively across 8 different languages, allowing you to scan multilingual user inputs for jailbreak attempts and maintain safety alignment globally.

Do I need PyTorch and transformers to scan for malicious prompts?▼

Yes, you need the transformers and torch libraries installed to run sequence classification and detect jailbreak attempts using the pre-trained transformer model.

What is the best way to secure LLMs from prompt injection?▼

Secure LLMs by filtering malicious prompts and third-party data through a pre-trained transformer model before processing, ensuring safety alignment and preventing unauthorized model behavior.

Related Skills

Explore More Software Engineering Skills→
Orchestra-ResearchOrchestra-Research
11.5k

prompt-guard

Detect prompt injections and jailbreak attempts in LLM inputs.

Official
Advanced
qcmuuqcmuu

prompt-guard

Detects prompt injection and jailbreak attempts in LLM inputs and retrieved context using Prompt-Guard-86M.

Community
Intermediate
NVIDIA-NeMoNVIDIA-NeMo
58

guardrails-plugin

Implements input/output guardrailing for chat-completions traffic in NeMo Inference Gateway.

Official
Advanced
patsnappatsnap
33

mab-fto-check

Analyze monoclonal antibody patent freedom-to-operate risk across sequence, modification, keyword, competitor, and jurisdiction filters.

Official
Advanced