216.73.216.6

Prompts as Code & Embedded Keys | The Hunt for LLM-Enabled Malware

· Published 25/09/2025 09:20 · Modified 25/09/2025 14:43

Export JSON

Essential information

Published
25/09/2025 09:20
Modified
25/09/2025 14:43
Tags
2025-09-25 api keys lamehug llm-enabled malware malterminal offensive tools promptlock prompts rkor threat hunting
Related entities
39 observables, 1 intrusion sets (apt), 8 techniques (mitre), 4 malware

Description

This research explores the challenges posed by , which can generate malicious logic at runtime. The study identifies characteristics of such malware, including embedded and specific prompt structures. Notable cases like and APT28's are examined. The researchers developed hunting strategies based on API key detection and prompt analysis, leading to the discovery of new samples, including ''. The implications for defenders are discussed, highlighting both the adaptability and potential brittleness of . The research also uncovered various leveraging LLMs for operational capabilities.

External references