Fake AI SDK packages on PyPI hid an infostealer inside PyTorch model files
Three PyPI packages posing as a Python SDK for a cloud AI lab service were uploaded on May 19, 2025 and stayed up less than a day, with about 1,600 downloads. On install they loaded a PyTorch model whose pickled data ran code that sent the user name, network address, organization name and .gitconfig contents to the attacker. ReversingLabs, which found them, judged the likely targets to be developers in China.
Sources
- Primary: https://www.reversinglabs.com/blog/malicious-attack-method-on-hosted-ml-models-now-targets-pypi
- Upstream: Editorial
- Entered by the cybermap.lol editors, with sources on the entry
Defenses for this class of incident
all categoriesA supply chain sits in these classes of the AI-security landscape. The companies below work on that class of problem. This is a taxonomy, not a claim that any of them would have changed this incident.
Vendor data: AI Security Startups Map by Prompt Security (CC BY 4.0), synced daily. startups.prompt.security. Paid placements are labelled Sponsored; HeimWall, which runs this site, is labelled Operator. 452 companies in the directory.
Wrong or missing? Email founders@heimwall.ai. Corrections are logged here, in place. How corrections and takedowns work.