Product
Qwen2.5-Coder-32B-Instruct
- First Reported
- Jun 11, 2026
- Latest Reported
- Nov 18, 2026
Reported Context (4)
- The malware calls Qwen2.5-Coder-32B-Instruct via the Hugging Face API using a hardcoded text prompt to generate commands, then executes them on the target. A Guide to MITRE ATLAS and AI System Attack Techniques
- attributed with medium confidence to APT28/UAC-0001 (IRON TWILIGHT) and described as using Qwen2.5-Coder-32B-Instruct via Hugging Face to generate commands at runtime. Sophos Finds Fake AI Installers Dominated Malware Cases
- attacker logic. Instead, it carries base64-encoded natural-language prompts, queries Alibaba’s Qwen 2.5-Coder-32B-Instruct model through the Hugging Face Inference API, and runs the Windows commands the model returns. APT28’s Tradecraft Evolves from X-Agent to LLM-Driven Malware
- attacker logic. Instead, it carries base64-encoded natural-language prompts, queries Alibaba’s Qwen 2.5-Coder-32B-Instruct model through the Hugging Face Inference API, and runs the Windows commands the model returns. Sekoia Traces APT28’s Tradecraft Evolution From X-Agent to LLM-Driven Malware
CVE (4)
Malware (18)
People (1)
Threat Actors (26)
MITRE ATT&CK (14)
Vendors (17)
Products (35)
Tools (12)
Industries (12)
Countries (11)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
