nuguard / README.md
davidmcmahon's picture
Upload README.md with huggingface_hub
9d962c8 verified
metadata
language: en
library_name: sklearn
tags:
  - safety
  - guardrail
  - content-filtering
license: mit

NuGuard - LLM Prompt Safety Classifier

A machine learning model for detecting potentially harmful prompts.

Model Details

  • Detects malicious content
  • Uses text and feature-based classification
  • Scikit-learn 1.6.1 compatible