McKern3l/RAGdrag
RAG pipeline security testing toolkit - 27 techniques across 6 kill chain phases, mapped to MITRE ATLAS
This toolkit helps security professionals evaluate how well their AI chatbots and Retrieval Augmented Generation (RAG) systems protect sensitive information. It allows you to simulate various attacks to see if your RAG pipeline might expose internal data, be tricked into giving wrong answers, or be manipulated by malicious inputs. Cyber security analysts, penetration testers, and AI system auditors would use this to harden their systems.
Use this if you need to thoroughly test the security of a RAG-powered chatbot or AI system to identify vulnerabilities that could lead to data leaks or system manipulation.
Not ideal if you are looking for a general-purpose AI development tool or a way to improve the performance of your RAG system, as this is solely focused on security testing.
Stars
13
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/McKern3l/RAGdrag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Bessouat40/RAGLight
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to...
datallmhub/ragctl
A powerful CLI tool to manage, test, and optimize RAG pipelines. Streamline your...
superagent-ai/super-rag
Super performant RAG pipelines for AI apps. Summarization, Retrieve/Rerank and Code Interpreters...
feld-m/rag_blueprint
A modular framework for building and deploying Retrieval-Augmented Generation (RAG) systems with...
mburaksayici/RAG-Boilerplate
RAG boilerplate with semantic/propositional chunking, hybrid search (BM25 + dense), LLM...