PromptGuard-AI

Name: PromptGuard-AI
Author: mirzayasirabdullahbaig07

34stars1forks

How to install PromptGuard-AI?

mirzayasirabdullahbaig07/promptguard-ai

$git clone https://github.com/mirzayasirabdullahbaig07/PromptGuard-AI

Installs into the current project.

Summary

> Real-time AI prompt threat detection powered by RAG, Groq, and llama-3.3-70b-versatile.

Files · 1

View on GitHub

README.md

1	# 🛡️ PromptGuard — AI Prompt Security Platform
2
3	> Real-time AI prompt threat detection powered by RAG, Groq, and llama-3.3-70b-versatile.
4
5	![PromptGuard](https://img.shields.io/badge/Model-llama--3.3--70b--versatile-red?style=flat-square)
6	![Groq](https://img.shields.io/badge/Inference-Groq-orange?style=flat-square)
7	![Embeddings](https://img.shields.io/badge/Embeddings-nomic--embed--text--v1__5-blue?style=flat-square)
8	![Deployment](https://img.shields.io/badge/Deploy-Netlify-00AD9F?style=flat-square)
9	![License](https://img.shields.io/badge/License-MIT-green?style=flat-square)
10
11	---
12
13	## 📌 Overview
14
15	PromptGuard is a single-file AI security platform that scans user prompts in real-time and classifies them as SAFE, SUSPICIOUS, or DANGEROUS. It uses Retrieval-Augmented Generation (RAG) to ground every verdict in your own security policy — uploading your rules once lets the system cite the exact policy clause violated in each scan.
16
17	Built entirely in vanilla HTML/CSS/JS with zero dependencies, it deploys to Netlify in under 60 seconds.
18
19	---
20
21	## ✨ Features
22
23	\| Feature \| Description \|
24	\|---\|---\|
25	\| 🔍 Real-time Prompt Scanning \| Classifies any prompt instantly with threat type, severity, and confidence \|
26	\| 📚 RAG-powered Policy Grounding \| Embeds your security policy and retrieves relevant chunks via cosine similarity \|
27	\| 🤖 llama-3.3-70b-versatile \| State-of-the-art LLM analysis running on Groq's ultra-fast inference API \|
28	\| 🧮 768-dim Vector Embeddings \| Uses `nomic-embed-text-v1_5` for high-quality semantic search \|
29	\| 💬 Policy Q&A Chatbot \| Ask natural language questions about your AI governance rules \|
30	\| 📊 Scan History & Stats \| Tracks all scans with verdicts, timestamps, and RAG grounding status \|
31	\| ⚡ Zero Dependencies \| Pure HTML/CSS/JS — no build step, no framework, no npm install \|
32
33	---
34
35	## 🚨 Threat Detection Categories
36
37	- Prompt Injection — Hidden instructions that attempt to override system rules
38	- Jailbreak — Role-play or fictional framing used to bypass safety guidelines
39	- Data Exfiltration — Requests to extract API keys, credentials, or context data
40	- Social Engineering — Emotional manipulation to extract sensitive information
41	- Policy Bypass — Attempts to circumvent your organization's AI usage policy
42	- PII Exposure — Prompts containing or requesting personally identifiable information
43
44	---
45
46	## 🏗️ Architecture
47
48	```
49	User Prompt
50	│
51	▼
52	┌─────────────────────────────────────┐
53	│ RAG Retrieval Layer │
54	│ Query → nomic-embed-text (768-dim) │
55	│ → Cosine Similarity → Top-K Chunks │
56	└─────────────────────────────────────┘
57	│ Relevant Policy Context
58	▼
59	┌─────────────────────────────────────┐
60	│ llama-3.3-70b-versatile │
61	│ (via Groq API) │
62	│ Structured JSON verdict output │
63	└─────────────────────────────────────┘
64	│
65	▼
66	SAFE / SUSPICIOUS / DANGEROUS
67	+ Threat Type + Severity + Policy Citation
68	```
69
70	---
71
72	## 🚀 Getting Started
73
74	### Prerequisites
75
76	- A free [Groq API key](https://console.groq.com) — takes ~30 seconds to create
77
78	### Setup
79
80	1. Clone the repository
81	```bash
82	git clone https://github.com/your-username/promptguard.git
83	cd promptguard
84	```
85
86	2. Add your Groq API key
87
88	Open `index.html` and replace the placeholder on this line:
89	```javascript
90	const GROQ_KEY = "YOUR_GROQ_API_KEY_HERE";
91	```
92
93	3. Open in browser
94	```bash
95	# Just open the file — no server needed
96	open index.html
97	```
98
99	That's it. No `npm install`, no build step.
100
101	---
102
103	## ☁️ Deploy to Netlify
104
105	```
106	1. Push the repository to GitHub
107	2. Go to netlify.com → "Add new site" → "Import from Git"
108	3. Select your repo — Netlify auto-detects the HTML file
109	4. Click Deploy
110	```
111
112	Your site is live in under 60 seconds. Set the `GROQ_KEY` as a Netlify environment variable if you want to avoid committing it.
113
114	---
115
116	## 🗂️ Project Structure
117
118	```
119	promptguard/
120	│
121	├── index.html # Entire application — UI, logic, RAG pipeline
122	└── README.

People who liked this also viewed

6 picks

Type

Resk-LLM Resk is a robust Python library designed to enhance security and manage context when interacting with LLMs. It provides a protective layer for API calls, safeguarding against common vulnerabilities and ensuring optimal performance. And safe layer again Prompt Injection. PromptsJun 202650022
agentic-ai-prompt-researchResearch into how agentic AI coding assistants work. Reconstructed prompt patterns, agent coordination, and security classificationPromptsMar 2026—2.5k
promptmapa security scanner for custom LLM applicationsPromptsDec 2025—1.2k
finite-monkey-engineAI engine for smart contract auditPromptsJan 2026—356
prompt-hacker-collectionsprompt attack-defense, prompt Injection, reverse engineering notes and examples | 提示词对抗、破解例子与笔记 PromptsFeb 2025—346
acipThe Advanced Cognitive Inoculation PromptPromptsMar 2026—329

PromptGuard-AI

34stars1forks

View on GitHub

How to install PromptGuard-AI?

mirzayasirabdullahbaig07/promptguard-ai

$git clone https://github.com/mirzayasirabdullahbaig07/PromptGuard-AI

Installs into the current project.

Summary

> Real-time AI prompt threat detection powered by RAG, Groq, and llama-3.3-70b-versatile.

Files · 1

View on GitHub

README.md

1	# 🛡️ PromptGuard — AI Prompt Security Platform
2
3	> Real-time AI prompt threat detection powered by RAG, Groq, and llama-3.3-70b-versatile.
4
5	![PromptGuard](https://img.shields.io/badge/Model-llama--3.3--70b--versatile-red?style=flat-square)
6	![Groq](https://img.shields.io/badge/Inference-Groq-orange?style=flat-square)
7	![Embeddings](https://img.shields.io/badge/Embeddings-nomic--embed--text--v1__5-blue?style=flat-square)
8	![Deployment](https://img.shields.io/badge/Deploy-Netlify-00AD9F?style=flat-square)
9	![License](https://img.shields.io/badge/License-MIT-green?style=flat-square)
10
11	---
12
13	## 📌 Overview
14
15	PromptGuard is a single-file AI security platform that scans user prompts in real-time and classifies them as SAFE, SUSPICIOUS, or DANGEROUS. It uses Retrieval-Augmented Generation (RAG) to ground every verdict in your own security policy — uploading your rules once lets the system cite the exact policy clause violated in each scan.
16
17	Built entirely in vanilla HTML/CSS/JS with zero dependencies, it deploys to Netlify in under 60 seconds.
18
19	---
20
21	## ✨ Features
22
23	\| Feature \| Description \|
24	\|---\|---\|
25	\| 🔍 Real-time Prompt Scanning \| Classifies any prompt instantly with threat type, severity, and confidence \|
26	\| 📚 RAG-powered Policy Grounding \| Embeds your security policy and retrieves relevant chunks via cosine similarity \|
27	\| 🤖 llama-3.3-70b-versatile \| State-of-the-art LLM analysis running on Groq's ultra-fast inference API \|
28	\| 🧮 768-dim Vector Embeddings \| Uses `nomic-embed-text-v1_5` for high-quality semantic search \|
29	\| 💬 Policy Q&A Chatbot \| Ask natural language questions about your AI governance rules \|
30	\| 📊 Scan History & Stats \| Tracks all scans with verdicts, timestamps, and RAG grounding status \|
31	\| ⚡ Zero Dependencies \| Pure HTML/CSS/JS — no build step, no framework, no npm install \|
32
33	---
34
35	## 🚨 Threat Detection Categories
36
37	- Prompt Injection — Hidden instructions that attempt to override system rules
38	- Jailbreak — Role-play or fictional framing used to bypass safety guidelines
39	- Data Exfiltration — Requests to extract API keys, credentials, or context data
40	- Social Engineering — Emotional manipulation to extract sensitive information
41	- Policy Bypass — Attempts to circumvent your organization's AI usage policy
42	- PII Exposure — Prompts containing or requesting personally identifiable information
43
44	---
45
46	## 🏗️ Architecture
47
48	```
49	User Prompt
50	│
51	▼
52	┌─────────────────────────────────────┐
53	│ RAG Retrieval Layer │
54	│ Query → nomic-embed-text (768-dim) │
55	│ → Cosine Similarity → Top-K Chunks │
56	└─────────────────────────────────────┘
57	│ Relevant Policy Context
58	▼
59	┌─────────────────────────────────────┐
60	│ llama-3.3-70b-versatile │
61	│ (via Groq API) │
62	│ Structured JSON verdict output │
63	└─────────────────────────────────────┘
64	│
65	▼
66	SAFE / SUSPICIOUS / DANGEROUS
67	+ Threat Type + Severity + Policy Citation
68	```
69
70	---
71
72	## 🚀 Getting Started
73
74	### Prerequisites
75
76	- A free [Groq API key](https://console.groq.com) — takes ~30 seconds to create
77
78	### Setup
79
80	1. Clone the repository
81	```bash
82	git clone https://github.com/your-username/promptguard.git
83	cd promptguard
84	```
85
86	2. Add your Groq API key
87
88	Open `index.html` and replace the placeholder on this line:
89	```javascript
90	const GROQ_KEY = "YOUR_GROQ_API_KEY_HERE";
91	```
92
93	3. Open in browser
94	```bash
95	# Just open the file — no server needed
96	open index.html
97	```
98
99	That's it. No `npm install`, no build step.
100
101	---
102
103	## ☁️ Deploy to Netlify
104
105	```
106	1. Push the repository to GitHub
107	2. Go to netlify.com → "Add new site" → "Import from Git"
108	3. Select your repo — Netlify auto-detects the HTML file
109	4. Click Deploy
110	```
111
112	Your site is live in under 60 seconds. Set the `GROQ_KEY` as a Netlify environment variable if you want to avoid committing it.
113
114	---
115
116	## 🗂️ Project Structure
117
118	```
119	promptguard/
120	│
121	├── index.html # Entire application — UI, logic, RAG pipeline
122	└── README.

People who liked this also viewed

6 picks

Type