Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
Ludwig versions up to and including 0.10.4 are vulnerable to insecure deserialization in the model serving component. When the ludwig serve command starts a model server, it loads model weight files with torch.load() without weights_only=True, so pickle-based objects are deserialized. An attacker who can supply a maliciously crafted PyTorch model file may be able to run arbitrary code on the host running the server. No fixed version is listed. Avoid serving model files from untrusted sources.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 9.8 | Critical | 3.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | OSV |
- CISA KEV Not listed.
- EPSS 0.0050, the 42nd percentile, on 10 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.