AI Runtime Security Tools

Sensitive Information Leakage: definition and example

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.

Facts read on .

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