LLM Prompt Injection

AML.T0051

Multi-turn or role-play attack escalates past system safety policy.

Tactics

Mitigations (4)

• Adversarial Input Detection AML.M0015
• Generative AI Guardrails AML.M0020
• Restrict AI Agent Tool Invocation on Untrusted Data AML.M0030
• Input and Output Validation for AI Agent Components AML.M0033