prompt-security/RAG_Poisoning_POC

Stealthy Prompt Injection and Poisoning in RAG Systems via Vector Database Embeddings

27
/ 100
Experimental

This project helps security professionals and developers understand how malicious instructions can be hidden within the data fed into AI systems that use Retrieval Augmented Generation (RAG). It shows how to inject harmful commands into document embeddings stored in a vector database, which can then manipulate an AI model's behavior. Anyone responsible for the security and integrity of AI applications using RAG systems would find this tool useful.

Use this if you are building or securing AI applications with RAG and need to identify and demonstrate a critical, stealthy prompt injection and data poisoning vulnerability through vector database embeddings.

Not ideal if you are looking for a general-purpose AI development framework or a tool to build secure RAG systems directly, as this is a proof-of-concept for demonstrating an attack.

AI-security prompt-injection RAG-systems vector-database-security LLM-vulnerability-testing
No License No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 5 / 25
Community 11 / 25

How are scores calculated?

Stars

12

Forks

2

Language

Python

License

Last pushed

Nov 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/prompt-security/RAG_Poisoning_POC"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.