✕ Exit
Prompt Injection Recipe
Ingredients
Ingredients
Large language model (such as GPT-3)
Web application with text input
Malicious SQL prompt or text prompt
Done
1
/
6
Understand the concept of prompt injection, which is injecting a malicious prompt into a large language model to alter the output or gain unauthorized access.
0:00
✕
+ Set Timer
Start
Cancel
← Prev
Next →