LLM Data Leakage

AML.T0057

Model echoes PII / training data / system prompt back to user.

Tactics

Mitigations (4)

• Encrypt Sensitive Information AML.M0012
• Generative AI Guardrails AML.M0020
• AI Telemetry Logging AML.M0024
• Input and Output Validation for AI Agent Components AML.M0033