seojoonkim/prompt-guard
Advanced prompt injection defense system for AI agents. Multi-language detection, severity scoring, and security auditing.
This project helps protect your AI agents and large language model (LLM) applications from being manipulated or leaking sensitive information. It takes user input or AI-generated responses and identifies attempts to bypass safety rules or extract confidential data like API keys. Security engineers, AI product managers, or anyone deploying an AI assistant would use this to ensure their AI behaves as intended and doesn't reveal secrets.
122 stars.
Use this if you are deploying AI agents or LLM-powered systems and need to prevent prompt injection attacks, detect data leakage, or ensure your AI adheres to its designed purpose across multiple languages.
Not ideal if you are looking for a general-purpose content moderation tool for user-generated text unrelated to AI agent security.
Stars
122
Forks
23
Language
Python
License
MIT
Category
Last pushed
Mar 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/seojoonkim/prompt-guard"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
LuciferForge/prompt-shield
Lightweight prompt injection detector. 22 attack patterns. Blocks jailbreaks before they reach...
Milbaxter/prompt-shield
AI agent security oracle. Scan any message for prompt injections. Pay with crypto. No accounts....
ShaggyT0701/prompt-shield
🛡️ Detect and block prompt injection attacks in LLM apps using pattern detectors, ML, and...