CX330Blake/Spell-Whisperer

Spell whisperer is a prompt injection challenges platform based on Grok API.

35
/ 100
Emerging

This project offers a platform where you can practice and learn how to "hack" large language models (LLMs) by testing their vulnerabilities to prompt injection. You input a prompt, and the system shows you how well you can bypass the LLM's intended instructions. It's designed for security researchers, AI developers, and anyone interested in understanding LLM security.

Use this if you want to develop or test your skills in finding and exploiting prompt injection vulnerabilities in AI models.

Not ideal if you are looking for a general-purpose LLM application or a tool for everyday AI tasks.

AI Security Prompt Engineering Red Teaming LLM Testing Cybersecurity Training
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

54

Forks

2

Language

TypeScript

License

GPL-3.0

Last pushed

Oct 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/CX330Blake/Spell-Whisperer"

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