Downloads · 30 days
0
modelaudit-mlflow-models-from-code-poc
celvexgroup/modelaudit-mlflow-models-from-code-poc
modelaudit-mlflow-models-from-code-poc is a machine learning model from celvexgroup. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Coordinated disclosure PoC for huntr (Protect AI MFV). Benign only.
Access
Public
Updated Jul 18, 2026
Repo size
74 B
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other2.4 KB · 54%
At a glance
- Access
- Public
- Created
- Jul 18, 2026
- Updated
- Jul 18, 2026
- SHA
- d5badb94
Model card
From the Hugging Face model README
PoC - modelaudit clean-passes MLflow models-from-code load-time RCE (BL-0109)
Coordinated disclosure PoC for huntr (Protect AI MFV). Benign only.
- Scanner: modelaudit==0.2.49 (+ modelscan==0.8.8). Format: MLflow (models-from-code).
modelaudit scan evil_mfc_model/-> 'Clean' / NO ISSUES FOUND / exit 0, butmlflow.pyfunc.load_model('evil_mfc_model')imports+executes evil_script.py at load time (RCE). MLflow models-from-code persists a model as a plain.pyentrypoint + an MLmodel YAML manifest with NO pickle; modelaudit classifies the.py(and the MLmodel) as 'unknown format' and skips them (core.py:7005-7008), and never follows the manifest's model_code_path.benign_mfc_model/is the same shape with no payload (also Clean = the miss is genuine);pickle_positive_control/model.pklfires CRITICAL (posix.system), proving the detector is live.- Benign: evil_script.py only os.system('touch <marker>') at import. No destructive action.
Files: evil_mfc_model/ (MLmodel + evil_script.py; scans Clean, RCE on load), benign_mfc_model/ (control), pickle_positive_control/model.pkl (fires). Full report in huntr submission.
- Created
- Jul 18, 2026
- Updated
- Jul 18, 2026