πŸ”¬
Vigil: Documentation
GitHub Repo
  • πŸ›‘οΈVigil
  • Overview
    • πŸ—οΈRelease Blog
    • πŸ› οΈInstall Vigil
      • πŸ”₯Install PyTorch (optional)
    • πŸ§ͺUse Vigil
      • βš™οΈConfiguration
        • πŸ”„Auto-updating vector database
      • πŸ—„οΈLoad Datasets
      • 🌐Web server
        • 🀝API Endpoints
        • πŸͺWeb UI playground
      • 🐍Python library
      • 🎯Scanners
        • πŸ€—Transformer
        • ❕YARA / Heuristics
        • πŸ“‘Prompt-response Similarity
        • πŸ’ΎVector database
        • 🐀Canary Tokens
    • πŸ›‘οΈCustomize Detections
      • 🌟Add custom YARA signatures
      • πŸ”’Add embeddings
      • 🐍Custom scanners
    • πŸͺ„Sample scan results
Powered by GitBook
On this page
  1. Overview
  2. πŸ§ͺUse Vigil
  3. 🎯Scanners

πŸ€—Transformer

The scanner uses the transformers library and a Hugging Face model built to detect prompt injection phrases. If the score returned by the model is above a defined threshold, Vigil will flag the analyzed prompt as a potential risk.

  • Model: JasperLS/gelectra-base-injection

This model is prone to false positives. If this is the only detection that fires, you should manually review the results before taking any action on the submitted prompt.

PreviousScannersNextYARA / Heuristics

Last updated 1 year ago