LLM02 · OWASP LLM Top 10

Sensitive Information Disclosure (LLM02)

An LLM reveals sensitive data through output. The data may come from training data, fine-tuning data, the system prompt, retrieved context (RAG), or other tenants if isolation fails.

Rank
LLM02 of 10
In the check
Cited by 1 of the 16 questions
LLM01
Prompt Injection
LLM02
Sensitive Information Disclosure
LLM03
Supply Chain
LLM04
Data and Model Poisoning
LLM05
Improper Output Handling
LLM06
Excessive Agency
LLM07
System Prompt Leakage
LLM08
Vector and Embedding Weaknesses
LLM09
Misinformation
LLM10
Unbounded Consumption
Figure 1. The OWASP LLM Top 10, with LLM02 marked.
In practice

What it looks like in practice

Three shapes this risk takes in real deployments.

Example 1

A fine-tuned model surfaces customer PII memorized from training data.

Example 2

A system prompt containing API keys is leaked through a clever prompt-injection attack.

Example 3

A RAG pipeline returns chunks from a document the requesting user did not have access to.

Controls

Controls that close it

These count toward the Data dimension of the check.

Data classification before training/fine-tuning/prompt inclusion

Output filtering and PII detection

Context isolation between tenants

Privacy testing including differential privacy where appropriate

Vendor data-handling contracts

Posture Check

Where the check cites it

The AI Posture Check cites OWASP LLM Top 10, including this entry, when placing you at Crawl, Walk, Run or Sprint.

Question the check may askDimensionCitation
Do you know what data people are putting into AI tools? Data OWASP LLM02, ISO 42001 Annex A.7
Ready when you are

Score yourself against this framework.

Five questions, each citing its source. You get your stage, your place on the chart and the one move that matters next.

  • A few minutes for most people
  • Free, from CWS
  • Your stage, the chart and the next move, by email or live with an engineer