Sunturai
Back to results
MediumSplunk security contentRod Soto +2Threat hunting

Windows Local LLM Framework Execution

The following analytic detects execution of unauthorized local LLM frameworks (Ollama, LM Studio, GPT4All, Jan, llama.cpp, KoboldCPP, Oobabooga, NutStudio) and Python-based AI/ML libraries (HuggingFace Transformers,…

Description

The following analytic detects execution of unauthorized local LLM frameworks (Ollama, LM Studio, GPT4All, Jan, llama.cpp, KoboldCPP, Oobabooga, NutStudio) and Python-based AI/ML libraries (HuggingFace Transformers, LangChain) on Windows endpoints by leveraging process creation events. It identifies cases where known LLM framework executables are launched or command-line arguments reference AI/ML libraries. This activity is significant as it may indicate shadow AI deployments, unauthorized model inference operations, or potential data exfiltration through local AI systems. If confirmed malicious, this could lead to unauthorized access to sensitive data, intellectual property theft, or circumvention of organizational AI governance policies.

Detection logic

Detection requirements

Platform
ContainersLinuxmacOSWindows

The rule states no platform. This is derived from the ATT&CK technique it maps to.

Log source category
crowdstrike_processrollup2sysmon_eventid_1windows_event_log_security_4688

Known benign triggers

  • Legitimate development, data science, and AI/ML workflows where authorized developers, researchers, or engineers intentionally execute local LLM frameworks (Ollama, LM Studio, GPT4All, Jan, NutStudio) for model experimentation, fine-tuning, or prototyping. Python developers using HuggingFace Transformers or LangChain for legitimate AI/ML projects. Approved sandbox and lab environments where framework testing is authorized. Open-source contributors and hobbyists running frameworks for educational purposes. Third-party applications that bundle or invoke LLM frameworks as dependencies (e.g., IDE plugins, analytics tools, chatbot integrations). System administrators deploying frameworks as part of containerized services or orchestrated ML workloads. Process name keyword overlap with unrelated utilities (e.g., "llama-backup", "janimation"). Recommended tuning — baseline approved frameworks and users by role/department, exclude sanctioned dev/lab systems via the filter macro, correlate with user identity and peer group anomalies before escalating to incident response.

Detections can measure how the public catalogue is used — which detections people look for, and which pages bring them here. It sets a cookie that recognises this browser for 180 days. It is never linked to an account and never follows you to other sites. Privacy notice