Use case sources
Source reports and analysis supporting this case are listed below. AITBM interpretation and any indicative scoring are derived from this public evidence.
- AIDEFEND SecureFlow — LAMEHUG: Malware Leveraging Dynamic AI-Generated Commands
- MITRE ATLAS case study AML.CS0044
- LameHug malware uses AI LLM to craft Windows data-theft commands in real-time (bleepingcomputer.com)
- UAC-0001 cyberattacks on the security and defense sector using the LAMEHUG software tool, which uses LLM (large language model) (CERT-UA#16039) (cert.gov.ua)
- APT28's New Arsenal: LAMEHUG, the First AI-Powered Malware (logpoint.com)
Incident overview
In July 2025, Ukrainian authorities reported the emergence of LAMEHUG, a new AI-powered malware attributed to the Russian state-backed threat actor APT28 (https://attack.mitre.org/groups/G0007/) (also tracked as Forest Blizzard or UAC-0001). LAMEHUG uses a large language model (LLM) to dynamically generate commands on the infected hosts.
The campaign began with a phishing attack leveraging a compromised government email account to deliver a malicious ZIP archive disguised as Appendix.pdf.zip. The archive contained the LAMEHUG malware, a Python-based executable, packed with PyInstaller. When executed, the malware makes calls to an LLM endpoint to generate malicious commands from natural language prompts. Dynamically generated commands may make the malware harder to detect. LAMEHUG was configured to collect files from the local system and exfiltrate them.
Why this record has no ERS
The AI element is the attacker's tooling: malware queries a hosted model to generate commands on an already compromised host. The victim systems are not AI deployments, and no control outcome of the model provider is reported, so the record fails the system and observation tests of the scorability admission test. It is retained as threat context.
Status: Not scorable by design · Classification: Incident · source date 2026-08-02 · primary evidence date 2025-06-03
SecureFlow attack flow
This record mirrors an AIDEFEND SecureFlow flow (MITRE ATLAS case-study conversion): an ordered attack path with MITRE ATLAS tactic and technique labels and the AIDEFEND controls matched to each step. The flow documents what happened and which controls apply; it does not establish an assessed deployment.
| MITRE ATLAS case study | AML.CS0044 (incident) |
|---|---|
| Target | Ukraine's security and defense sector |
| Actor | APT28 |
| Reporter | CERT-UA |
| Primary evidence date | 2025-06-03 |
| SecureFlow record updated | 2026-08-02 |
| AI layers | AI infrastructure |
| Risk impact | Resource hijacking / cost |
| Affected components | Qwen 2.5 Coder 32B Instruct model, Hugging Face inference API, LAMEHUG malware, compromised host egress path |
Attack steps
| # | Step | ATLAS tactic / technique |
|---|---|---|
| 1 | Compromise Government Email AccountAPT28 gained access to a compromised official email account. | AML.TA0004 AML.T0012 |
| 2 | Send Phishing Email with Malicious ArchiveAPT28 sent a phishing email from the compromised account with an attachment containing malware. | AML.TA0015 AML.T0052 |
| 3 | Impersonate Ministry RepresentativeThe email impersonated a government ministry representative. | AML.TA0007 AML.T0073 |
| 4 | Masquerade Malware as PDF AttachmentThe attachment was called "Appendix.pdf.zip" which could confuse the recipient into thinking it was a legitimate PDF file. | AML.TA0007 AML.T0074 |
| 5 | Execute PyInstaller .pif PayloadThe attachment contained an executable file with a .pif extension, created using PyInstaller from Python source code which CERT-UA classified as LAMEHUG malware. Files with the .pif extension are executable on Windows. | AML.TA0005 AML.T0011 |
| 6 | Generate Malicious Commands via LLM APIThe LAMEHUG malware abused the Qwen 2.5 Coder 32B Instruct model via its Hugging Face API to generate malicious commands from natural language prompts. | AML.TA0001 AML.T0102 |
| 7 | Collect and Stage Local FilesThe LAMEHUG malware used the AI generated commands to collect system information (saved to `%PROGRAMDATA%\info\info.txt`) and recursively searched Documents, Desktop, and Downloads to stage files for exfiltration. | AML.TA0009 AML.T0037 |
| 8 | Exfiltrate Data via SFTP and HTTPThe LAMEHUG malware exfiltrated collected data to attacker controlled servers via SFTP or HTTP POST requests. | AML.TA0010 AML.T0025 |
Threat references
Summary and attack steps reproduced from AIDEFEND SecureFlow (https://aidefendlabs.com/en/secureflow/?flow=atlas-aml-cs0044-lamehug-ai-generated-commands; AIDEFEND content CC BY 4.0), converted from MITRE ATLAS case study AML.CS0044 (Apache License 2.0; MITRE ATLAS is a trademark of The MITRE Corporation).
AIDEFEND evidence routes
AIDEFEND defences → AITBM sub-metrics
Identifiers are quoted as they appear on the AIDEFEND in Action brief or in the AIDEFEND SecureFlow defense map (audited AIDEFEND dataVersion 2026.10.15); the sub-metric mapping is AITBM's own, from the specification's AIDEFEND tables reconciled at catalogue data version 2026.10.15. AIDEFEND renumbers identifiers between releases, so the data version travels with every mapping and neither side's IDs should be cited without one. A mapping identifies a possible evidence route; a recommendation does not prove that the control was implemented or effective and receives no scoring credit by itself.
| Technique | Defence | Priority | Evidences |
|---|---|---|---|
| AID-D-003.001 | Harmful Text & Token Output Policy-Violation DetectionExact SecureFlow defense-map identifier (flow atlas-aml-cs0044-lamehug-ai-generated-commands), verified against AIDEFEND dataVersion 2026.10.15; matched to attack step step-6. Presence supplies no score credit. | Candidate evidence route | Ro-3 Cn-1 Cn-3 Cn-7 |
| AID-H-006.002 | Text, Markup & Structured Output Sanitization and Release GateExact SecureFlow defense-map identifier (flow atlas-aml-cs0044-lamehug-ai-generated-commands), verified against AIDEFEND dataVersion 2026.10.15; matched to attack step step-6. Presence supplies no score credit. | Candidate evidence route | Ro-3 Cn-3 |
| AID-I-002.002 | Secure External AI Service ConnectivityExact SecureFlow defense-map identifier (flow atlas-aml-cs0044-lamehug-ai-generated-commands), verified against AIDEFEND dataVersion 2026.10.15; matched to attack step step-6. Presence supplies no score credit. | Candidate evidence route | Cn-4 |
Related AITBM rubrics
Sources
- AIDEFEND SecureFlow — LAMEHUG: Malware Leveraging Dynamic AI-Generated Commands
- MITRE ATLAS case study AML.CS0044
- LameHug malware uses AI LLM to craft Windows data-theft commands in real-time (bleepingcomputer.com)
- UAC-0001 cyberattacks on the security and defense sector using the LAMEHUG software tool, which uses LLM (large language model) (CERT-UA#16039) (cert.gov.ua)
- APT28's New Arsenal: LAMEHUG, the First AI-Powered Malware (logpoint.com)