Database/AI/ML frameworks & serving
MLflow (model flavors): Deserialization RCE from a maliciously uploaded model (one of a family: 37052–37060)
CVSS 8.8CVE-2024-37052AI/ML frameworks & servingcurated
Impact
Deserialization RCE from a maliciously uploaded model (one of a family: 37052–37060)
Who can reach it
Customer-supplied model artifact loaded via mlflow.pyfunc.load_model
What to do
No format fix — every MLflow model flavor wraps pickle. Restrict who can register models and sandbox model-load workers
References
Related entries
- MLflow (recipes / pyfunc): RCE via a maliciously crafted MLprojectCVE-2024-37061 · MLflow (recipes / pyfunc)High
- ONNX (`download_model_with_test_data`): Arbitrary file overwrite from a crafted model archiveCVE-2024-5187 · ONNX (`download_model_with_test_data`)High
- LocalAI: RCE — the backend accepts inputs beyond the config pathCVE-2024-6983 · LocalAIHigh
- llama.cpp (vocab): Attacker-supplied GGUF vocabulary triggers memory corruptionCVE-2025-49847 · llama.cpp (vocab)High
- ONNX (`save_external_data`): Path traversalCVE-2025-51480 · ONNX (`save_external_data`)High
- vLLM (multimodal embeddings): Memory corruptionCVE-2025-62164 · vLLM (multimodal embeddings)High
This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.