ATLAS Landscape
AML.T0102

Generate Malicious Commands

Adversaries may use large language models (LLMs) to dynamically generate malicious commands from natural language. Dynamically generated commands may be harder detect as the attack signature is constantly changing. AI-generated commands may also allow adversaries to more rapidly adapt to different environments and adjust their tactics. Adversaries may utilize LLMs present in the victim's environment or call out to externally hosted services. [APT28](https://attack.mitre.org/groups/G0007) utilized a model hosted on HuggingFace in a campaign with their LAMEHUG malware [\[1\]][1]. In either case prompts to generate malicious code can blend in with normal traffic. [1]: https://logpoint.com/en/blog/apt28s-new-arsenal-lamehug-the-first-ai-powered-malware

Severity CVE CVSS
CRITICAL CVE-2026-41265 9.8
CRITICAL CVE-2026-41264 9.8
HIGH CVE-2026-42079 8.6
HIGH GHSA-f228-chmx-v6j6 8.3
CRITICAL GHSA-v38x-c887-992f
UNKNOWN CVE-2026-33873
UNKNOWN CVE-2024-10950
UNKNOWN CVE-2024-48919