← Back to learn hub
LLM04

Data Poisoning

Knowledge base injection, malicious context influence

What is Data Poisoning?

Data Poisoning is ranked LLM04 in the OWASP LLM Top 10 (2025) — the industry-standard taxonomy for large language model security risks. It represents one of the most commonly exploited vulnerability classes in production AI deployments.

How Nemesis tests for it

Data Poisoning

Tests whether injected malicious content in a simulated knowledge base influences model outputs and decisions.

6 test casesNIST SI-7NIST CM-3NIST SA-10

Test your model for Data Poisoning

Run the full LLM04 attack suite against your LLM in minutes.

Run free scan →