Staging environment
Digital asset

Prompt Injections are the #1 Security Risk in LLMs… We created a list of the 28 different Prompt Inj

Sander Schulhoff

Sander Schulhoff

Ran the 1st AI Red Teaming CTF w/ OpenAI

See all products from Learn Prompting Co.

We collected a dataset of over 600,000 prompt injections and developed a taxonomy of the 28 different Prompt Injection techniques that you must know to deploy secure AI models.

Free

I want this list!