Spaces:
Paused
Paused
A newer version of the Gradio SDK is available: 6.19.0
metadata
title: Prompt Injection Detector
emoji: 🛡️
colorFrom: red
colorTo: yellow
sdk: gradio
sdk_version: 5.9.1
python_version: '3.11'
app_file: app.py
pinned: false
license: mit
Prompt Injection Detector
Detects adversarial text designed to hijack LLM instructions (prompt injection attacks).
Model: Builder117/distilbert-prompt-injection
Severity levels:
- 🔴 HIGH — injection confidence ≥ 0.90
- 🟡 MEDIUM — injection confidence ≥ 0.70
- 🟠 LOW — injection confidence ≥ 0.50
- 🟢 CLEAN — injection confidence < 0.50