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
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 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
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 ask | Dimension | Citation |
|---|---|---|
| Do you know what data people are putting into AI tools? | Data | OWASP LLM02, ISO 42001 Annex A.7 |
Other frameworks the check cites
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