rb81/prompt-hacking-classifier

A flexible and portable solution that uses a single robust prompt and customized hyperparameters to classify user messages as either malicious or safe, helping to prevent jailbreaking and manipulation of chatbots and other LLM-based solutions.

29
/ 100
Experimental

This project helps protect your chatbots and large language model (LLM) applications from being manipulated or 'jailbroken' by malicious users. It takes incoming user messages and classifies them as either safe or malicious, outputting a simple 'true' or 'false'. Anyone managing or deploying LLM-powered solutions, such as product managers, AI ethics specialists, or operations engineers, would use this to enhance security.

No commits in the last 6 months.

Use this if you need a flexible and cost-effective way to prevent malicious users from bypassing your chatbot's intended behavior or extracting sensitive information.

Not ideal if you require a highly sophisticated, multi-layered security system beyond simple message classification, or if you need an actively maintained solution.

chatbot-security LLM-safety AI-content-moderation prompt-injection-prevention AI-governance
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

16

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/rb81/prompt-hacking-classifier"

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