Feb 23, 2023
Researchers define indirect prompt injection against LLM-integrated apps including Bing Chat
Greshake et al. describe indirect prompt injection, where instructions planted in data an LLM application retrieves are treated as commands. The paper demonstrates the attack class against Bing's GPT-4 powered chat, code-completion engines, and synthetic GPT-4 applications, and catalogs impacts including data theft, worming, and unauthorized API calls.