Database/AI/ML frameworks & serving
MLflow (recipes / pyfunc): RCE via a maliciously crafted MLproject
CVSS 8.8CVE-2024-37061AI/ML frameworks & servingcurated
Impact
RCE via a maliciously crafted MLproject
Who can reach it
Customer-supplied MLproject/recipe run by the platform
What to do
Upgrade. If the provider runs a managed MLflow, tenant projects execute in the provider plane
References
Related entries
- ONNX (`download_model_with_test_data`): Arbitrary file overwrite from a crafted model archiveCVE-2024-5187 · ONNX (`download_model_with_test_data`)High
- llama.cpp: unvalidated token IDs in a /completion prompt read embedding memory out of bounds or crash the serverCVE-2024-58400 · llama.cpp llama-server (/completion token ID validation)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.