S-08Malicious Retrieved Content
RAG faithfully retrieves whatever ranks well — including documents crafted to rank well and mislead.
Further reading
- PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models Zou et al., USENIX Security 2025
- Not what you’ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection Greshake et al., AISec 2023