Pluto Security details the Load/Mine mining campaign on Hugging Face
Pluto Security détaille une campagne de cryptominage Load/Mine sur Hugging Face
Pluto Security released the Load/Mine report, stating that 31 malicious model repositories on Hugging Face (distributed across 7 accounts, plus a ModelScope mirror) spread miners and backdoors, with a cumulative 29,818 downloads recorded, or 32,376 when 13 associated repositories are included. The report said the second wave of 19 repositories had more than 29,000 downloads and was still online 8 days after Pluto notified them. The payload exploits Transformers importing the repository's Python code via config.json's auto_map under trust_remote_code=True, executing it before loading weights; the report also cites CVE-2026-22807, stating that vLLM 0.10.1 through 0.14.0 did not validate this parameter before the fix. The report said the first wave's wallet received about 2,276 PRL, about $5,000. None of the 12 repositories in the first wave was reported by security scanners, and the second wave's main payload was judged safe by all scanners.
The report gives the download scale of the malicious model repositories, their persistence methods and scanner misses, which can be used to check whether one's own inference deployment has loaded similar repositories.