MITRE ATLASsub-technique

AML.T0051.000 Direct

Published 2023-10-25 Modified 2023-10-25 Official page ↗
Tactics
Execution
Created
2023-10-25

Description

An adversary may inject prompts directly as a user of the LLM. This type of injection may be used by the adversary to gain a foothold in the system or to misuse the LLM itself, as for example to generate harmful content.

Related

Subtechnique of · MITRE ATLAS (1)

Tactic · MITRE ATLAS (1)

Referenced by MITRE ATLAS · mitigates (2)

  • AML.M0033 Input and Output Validation for AI Agent Components mitigation
  • AML.M0024 AI Telemetry Logging mitigation