thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Intermediate

Sensitive Information Disclosure

An LLM application risk where the model reveals confidential data, PII or secrets in its outputs.

Definition

Leaks can come from training data memorization, RAG over improperly permissioned documents, or system prompts containing secrets. Mitigations include data minimization, PII redaction, permission-aware retrieval and output filtering.

Exam tip

Permission-aware retrieval prevents RAG systems from leaking documents users should not see.

Related terms