Fujitsu OneCompression < 1.2.1 Arbitrary Code Execution via torch.load Deserialization
Key facts
- Attack vector
- Local
- Privileges required
- None
- User interaction
- Active
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- Code execution
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-502.
Summary
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| Fujitsu Research | OneCompression | before 1.2.1 | 1.2.1 | Patch available | CNA |
- OneCompression VendorFujitsu Research Affected before 1.2.1 Fixed in 1.2.1 Patch available CNA
Remediation
- Fix · CNA OneCompression (Fujitsu Research) Fixed in 1.2.1
Timeline
- 2026-10-02 Threatist record created from CVE-2026-73325
- 2026-10-03 Alias added: GHSA-f3q7-jj9x-2wjr
References
Sources
- CVE-2026-73325 · CVE Program
- CVE-2026-73325 · NVD
- FIRST EPSS
- GHSA-f3q7-jj9x-2wjr · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences