ModelScan
Protect AIModelScan checks machine-learning model files for code that would run when the model is loaded, an attack known as model serialization. It reads Pickle, H5, Keras and SavedModel files without loading them, covering models from PyTorch, TensorFlow, Keras, scikit-learn and XGBoost, and ranks what it finds by severity. Protect AI publishes it as a command-line tool and Python package.
Openness
5 medium confidence- license
- Apache-2.0 (OSI)
- source
- public (the full scanner and CLI)
- core features withheld
- no — ModelScan is a complete scanner that runs locally; Protect AI's Guardian is a separate enterprise product, not a withheld ModelScan module
ModelScan's code is Apache-2.0, and the published scanner is complete and runs locally for the formats it supports. Protect AI sells Guardian as a separate enterprise product with newer scanners and broader model support; it is not a part of ModelScan kept back for paying customers.
- https://pypi.org/pypi/modelscan/json recorded 2026-11-12
The PyPI record for modelscan 0.8.8, uploaded 2026-02-18, gives license "Apache-2.0" and the classifier "License :: OSI Approved :: Apache Software License", authored by ProtectAI.
- https://raw.githubusercontent.com/protectai/modelscan/HEAD/LICENSE recorded 2026-11-12
The LICENSE body is the Apache License 2.0 text with the notice "Copyright 2023 Protect AI".
- https://raw.githubusercontent.com/protectai/modelscan/HEAD/README.md recorded 2026-11-12
The README says "ModelScan offers robust open-source scanning. If you need comprehensive AI security, consider Guardian. It is our enterprise-grade model scanning product", and lists among Guardian's features "Access our latest scanners, broader model support, and automatic model format detection".
- https://ungh.cc/repos/protectai/modelscan/files/main recorded 2026-11-12
The repository file listing shows the modelscan package with its scanners and tests, and no ee, enterprise, commercial or proprietary path.
Adoption
2 high confidencePyPI downloads of the modelscan package, the tool's only distribution. Scans in automated pipelines can install it again on every run, so a download is not one user.
- https://pypistats.org/api/packages/modelscan/recent recorded 2026-11-12
"last_month":45087 for modelscan
- https://raw.githubusercontent.com/protectai/modelscan/HEAD/README.md recorded 2026-11-12
The README installs the tool with "pip install modelscan" and links the PyPI project page.
Capability
3 medium confidenceModelScan catches one class of attack, malicious code hidden in a model file, before the model is loaded, across the main serialization formats. It does not probe a running model for jailbreaks, leakage or toxic output, which garak does across many model providers, so it sits a step below garak.
- https://raw.githubusercontent.com/protectai/modelscan/HEAD/README.md recorded 2026-11-12
The README's support table marks Pickle, Protocol Buffer (SavedModel), HD5 and Keras V3 formats as supported for PyTorch, TensorFlow, Keras and classic ML libraries "pickle.dump(), dill.dump(), joblib.dump(), cloudpickle.dump()", and ranks unsafe code as CRITICAL, HIGH, MEDIUM and LOW.
Verified 2026-11-12