The Aoki infostealer malware has recently evolved to target credentials from AI coding assistants such as Claude, OpenAI's Codex, Cursor, Codeium, and Gemini. It steals API keys, tokens, and session files that could allow attackers to impersonate legitimate users and access connected repositories, cloud services, and CI/CD pipelines. In addition to AI-related credentials, Aoki collects data from browsers, cryptocurrency wallets, password managers, messaging apps, gaming platforms, VPN and FTP clients. The stolen data is sent to command-and-control servers. This indicates that AI credentials are increasingly valuable to cybercriminals, alongside traditional targets like payment card data and cryptocurrency wallets.
This research explores the challenges posed by LLM-enabled malware, which can generate malicious logic at runtime. The study identifies characteristics of such malware, including embedded API keys and specific prompt structures. Notable cases like PromptLock and APT28's LameHug are examined. The researchers developed hunting strategies based on API key detection and prompt analysis, leading to the discovery of new samples, including 'MalTerminal'. The implications for defenders are discussed, highlighting both the adaptability and potential brittleness of LLM-enabled malware. The research also uncovered various offensive tools leveraging LLMs for operational capabilities.
