AI engineering glossary · Evals guardrails AI security
What is sensitive information disclosure?
Sensitive information disclosure: An OWASP-listed risk where a model or its application reveals confidential data, such as personal details, credentials, proprietary code or internal documents, through its responses. Causes include memorised training data, poor access controls on retrieval and leaked prompts.
Sensitive information disclosure: an example
A staff assistant answers a question with another employee's salary because its document index ignored access rules.
Related terms
More Evals guardrails AI security terms
- Sleeper agents
- Spotlighting
- STRIDE threat model
- Structured output validation
- SWE-bench
- Synthetic test data
- System prompt extraction
- Threat modelling
Where you learn it
Sensitive information disclosure is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.