User Execution

This technique has been observed in real-world attacks on AI systems.

An adversary may rely upon specific actions by a user in order to gain execution. Users may inadvertently execute unsafe code introduced via [AI Supply Chain Compromise](/techniques/AML.T0010). Users may be subjected to social engineering to get them to execute malicious code by, for example, opening a malicious document file or link.

Sub-techniques 4

AML.T0011.000 Unsafe AI Artifacts Realized AML.T0011.001 Malicious Package Realized AML.T0011.002 Poisoned AI Agent Tool Realized AML.T0011.003 Malicious Link Demonstrated