# Sensitive Information Leakage: definition and example

URL: https://airuntimesecuritytools.com/glossary/sensitive-information-leakage/
Updated: 2026-11-16

Sensitive information leakage is the exposure of personal data, credentials, business secrets or model internals through an AI system's output. OWASP lists it as its second risk for LLM applications. Controls combine data sanitization, output filtering and limits on what the model can reach.

## Example

OWASP notes that restrictions placed in a system prompt about what data to return may not always be honored and could be bypassed via prompt injection.

## Sources

- [OWASP LLM02:2025, sensitive information](https://genai.owasp.org/llmrisk/llm022025-sensitive-information-disclosure/) (genai.owasp.org), read 2026-11-16

## Related pages

- [PII Redaction](/glossary/pii-redaction/)
- [Output Filtering](/glossary/output-filtering/)
- [System Prompt Leakage](/glossary/system-prompt-leakage/)
- [All glossary terms](/glossary/)
- [SDK Integration](/glossary/sdk-integration/)
- [Sidecar Deployment](/glossary/sidecar-deployment/)
- [Guides](/guides/)
