F-MFV-008: ModelScan misses bundled Python code execution in PyTorch Package archives
This repository contains a gated proof-of-concept model artifact for a Huntr Model File Vulnerability submission.
Warning: do not load this artifact outside an isolated test environment. The payload is intentionally harmless and writes only local marker files during controlled reproduction, but it demonstrates a model-load execution path.
Target
- Finding:
F-MFV-008 - Target: PyTorch Package / ModelScan
- Scanner: ModelScan
0.8.8
Summary
The PyTorch Package artifact carries bundled Python source that executes a harmless marker during PackageImporter.load_pickle while ModelScan scans only the pickle payload and skips the package source file.
Files
malicious_package.pt- SHA256:
14d118fd4a7af62fba2e6927b4504bd51ecac244e44c2fccb80f396d9c3532bf
- SHA256:
Access
This public repository is gated with manual access review for Huntr MFV triage. protectai-bot has been granted access.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support