Slide 4 of 27
Part 1 · What Is It?Slide 4
Slide 4 · The Definition
Now the official definition will make sense.
OWASP LLM08:2025 — Vector and Embedding Weaknesses.
OWASP’s Definition

Vectors and embeddings vulnerabilities present significant security risks in systems utilizing Retrieval-Augmented Generation (RAG) with Large Language Models. These weaknesses arise from how vectors are created, stored, or accessed — allowing attackers to introduce harmful content, alter outputs, or expose confidential data.

Breaking It Down

“How vectors are created” — what content enters the embedding pipeline (hidden text, adversarial formatting)
“How vectors are stored” — whether the vector store is encrypted and access-controlled
“How vectors are accessed” — whether retrieval enforces permissions at query time

New in 2025

LLM08 is one of three categories added for the 2025 edition of the OWASP LLM Top 10. Its addition reflects how rapidly RAG-based applications have become the dominant deployment pattern for enterprise AI. If your system uses an LLM with any private knowledge base, this category applies to you.

← BackNext → Why vectors are uniquely vulnerable