Threat intelligence / Technique

User Execution

An adversary may rely upon a user to load, execute, interpret, or otherwise use a malicious or unsafe artifact. In AI systems, user execution may include loading a model or causing an inference runtime to process executable or behavior-shaping components bundled with an AI artifact. The resulting effect may include host code execution or malicious AI behavior. 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.

Technique

TypeTechnique

External ID—

First seen2026-08-14

Last seen2026-08-14

Confidence

—

An adversary may rely upon a user to load, execute, interpret, or otherwise use a malicious or unsafe artifact. In AI systems, user execution may include loading a model or causing an inference runtime to process executable or behavior-shaping components bundled with an AI artifact. The resulting effect may include host code execution or malicious AI behavior. 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.

12 recorded

Relationships

mitigates

from AI Bill of Materials

Mitigation

mitigates

from Restrict Library Loading

Mitigation

mitigates

from User Training

Mitigation

mitigates

from Verify AI Artifacts

Mitigation

mitigates

from Vulnerability Scanning

Mitigation

subtechnique-of

from Malicious Link

Technique

subtechnique-of

from Malicious Package

Technique

subtechnique-of

from Poisoned AI Agent Tool

Technique

subtechnique-of

from Unsafe AI Artifacts

Technique

uses

from Arbitrary Code Execution with Google Colab

Campaign

uses

from Cross-Site Scripting via Prompt Manipulation in Lenovo AI Chatbot

Campaign

uses

from LAMEHUG: Malware Leveraging Dynamic AI-Generated Commands

Campaign

1 external

References

mitre-atlas

AML.T0011