AML.T0094
Delay Execution of LLM Instructions
Adversaries may include instructions to be followed by the AI system in response to a future event, such as a specific keyword or the next interaction, in order to evade detection or bypass controls placed on the AI system.
- Tactic Defense Evasion
- Maturity: Demonstrated
- Generative AI
- Agentic AI
Mitigations
- Generative AI GuardrailsAML.M0020
Guardrails are safety controls placed between users, tools, and generative AI models to evaluate prompts, retrieved context, model outputs, and agent actions before they are accepted, executed, or shown to a user.
Technical - AI
From MITRE ATLAS 2026.10, Copyright 2021-2026 MITRE, Apache License 2.0.