All categories

RAG Poisoning

Attacks that corrupt the retrieval layer of an AI app, causing the model to ground its answers on attacker-controlled content.

OWASP LLM: LLM04high: 4medium: 4
highLLM04

Embedding collision

Attacker crafts content whose embedding is close to a high-value query, ensuring it gets retrieved.

highLLM04

Knowledge base write via feedback loop

User feedback (chat turns, thumbs-up examples) gets fed back into the retrieval index, letting attackers inject persistent content.

mediumLLM04

Metadata injection

Document metadata fields like title or author are concatenated into the prompt and contain the attack payload.

mediumLLM04

HTML comment payloads

Documents indexed from web crawls contain HTML comments with attacker instructions; comments survive into the prompt.

mediumLLM04

Duplicate flooding

Attacker submits many slight variants of the same poisoned content to dominate top-k retrieval for a target query.

highLLM04

Vector pinning

Attacker uses a long-lived public document (Wikipedia stub, GitHub README) as a pinned source the AI app trusts.

mediumLLM04

Image document poisoning

PDFs and images uploaded to the KB contain hidden text layers with attack instructions.

highLLM02

Training data leakage via RAG

Attacker queries craft retrieval that exposes private documents the operator forgot to filter from the index.