Update README.md

README.md

@@ -1,3 +1,35 @@
+---
+title: "LLMGuard – Prompt Injection + Moderation Toolkit"
+emoji: 🛡️
+colorFrom: indigo
+colorTo: blue
+sdk: streamlit
+sdk_version: 1.32.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+# 🛡️ LLMGuard – Prompt Injection + Moderation Toolkit
+
+LLMGuard is a real-time LLM security and moderation toolkit designed to:
+- Detect and block prompt injection attacks
+- Moderate harmful, unsafe, or policy-violating content
+- Log moderation events for auditing
+
+**Features:**
+- 🔍 Prompt Injection Detection
+- ⚠️ Harmful Content Moderation
+- 🗂 Moderation History Panel
+- 🌐 Deployable via Docker / Hugging Face Spaces / Streamlit Cloud
+
+## 🚀 How to run locally
+
+```bash
+pip install -r requirements.txt
+streamlit run app.py
+
+
 #  LLMGuard – Prompt Injection Detection
 
 This Streamlit app detects prompt injection attempts in real-time using a fine-tuned Flan-T5 model hosted on Hugging Face.