CVE-2026-73325
Fujitsu Research's OneCompression library before 1.2.1 contains an unsafe deserialization vulnerability that allows attackers to execute arbitrary code by supplying a crafted model.pt checkpoint file, as QuantizedModelLoader.load_quantized_model_pt()…
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.26%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
Fujitsu Research's OneCompression library before 1.2.1 contains an unsafe deserialization vulnerability that allows attackers to execute arbitrary code by supplying a crafted model.pt checkpoint file, as QuantizedModelLoader.load_quantized_model_pt() unconditionally calls torch.load with weights_only=False, invoking Python's pickle machinery during deserialization. Attackers can embed malicious __reduce__ methods in a crafted model checkpoint to execute arbitrary Python code, including system commands, when the library loads the file from a caller-selected model directory.
- CVSS 4.0
- 8.4 HIGHCVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
- EPSS
- 0.26% probability · 18th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-502
- Source
- disclosure@vulncheck.com
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.