Fujitsu Research OneCompression up to 1.2.0 QuantizedModelLoader.load_quantized_model_pt deserialization

CVSS Meta Temp Score
CVSS is a standardized scoring system to determine possibilities of attacks. The Temp Score considers temporal factors like disclosure, exploit and countermeasures. The unique Meta Score calculates the average score of different sources to provide a normalized scoring system.
Current Exploit Price (≈)
Our analysts are monitoring exploit markets and are in contact with vulnerability brokers. The range indicates the observed or calculated exploit price to be seen on exploit markets. A good indicator to understand the monetary effort required for and the popularity of an attack.
CTI Interest Score
Our Cyber Threat Intelligence team is monitoring different web sites, mailing lists, exploit markets and social media networks. The CTI Interest Score identifies the interest of attackers and the security community for this specific vulnerability in real-time. A high score indicates an elevated risk to be targeted for this vulnerability.
6.3$0-$5k4.73

Summaryinfo

A vulnerability, which was classified as critical, was found in Fujitsu Research OneCompression up to 1.2.0. This impacts the function QuantizedModelLoader.load_quantized_model_pt. Such manipulation leads to deserialization. This vulnerability is referenced as CVE-2026-73325. It is possible to launch the attack remotely. No exploit is available.

Detailsinfo

A vulnerability, which was classified as critical, has been found in Fujitsu Research OneCompression up to 1.2.0. Affected by this issue is the function QuantizedModelLoader.load_quantized_model_pt. The manipulation with an unknown input leads to a deserialization vulnerability. Using CWE to declare the problem leads to CWE-502. The product deserializes untrusted data without sufficiently verifying that the resulting data will be valid. Impacted is confidentiality, integrity, and availability. CVE summarizes:

Fujitsu Research's OneCompression library 1.2.0 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.

The advisory is available at pypi.org. This vulnerability is handled as CVE-2026-73325 since 08/11/2026. The exploitation is known to be easy. The attack may be launched remotely. Technical details are known, but there is no available exploit. The structure of the vulnerability defines a possible price range of USD $0-$5k at the moment (estimation calculated on 08/12/2026).

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Productinfo

Vendor

Name

Version

License

CPE 2.3info

CPE 2.2info

CVSSv4info

VulDB Vector: 🔒
VulDB Reliability: 🔍

CVSSv3info

VulDB Meta Base Score: 6.3
VulDB Meta Temp Score: 6.3

VulDB Base Score: 6.3
VulDB Temp Score: 6.3
VulDB Vector: 🔒
VulDB Reliability: 🔍

CVSSv2info

AVACAuCIA
💳💳💳💳💳💳
💳💳💳💳💳💳
💳💳💳💳💳💳
VectorComplexityAuthenticationConfidentialityIntegrityAvailability
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock

VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍

Exploitinginfo

Class: Deserialization
CWE: CWE-502 / CWE-20
CAPEC: 🔒
ATT&CK: 🔒

Physical: No
Local: No
Remote: Yes

Availability: 🔒
Status: Not defined
Price Prediction: 🔍
Current Price Estimation: 🔒

0-DayUnlockUnlockUnlockUnlock
TodayUnlockUnlockUnlockUnlock

Threat Intelligenceinfo

Interest: 🔍
Active Actors: 🔍
Active APT Groups: 🔍

Countermeasuresinfo

Recommended: no mitigation known
Status: 🔍

0-Day Time: 🔒

Timelineinfo

08/11/2026 CVE reserved
08/12/2026 +1 days Advisory disclosed
08/12/2026 +0 days VulDB entry created
08/12/2026 +0 days VulDB entry last update

Sourcesinfo

Advisory: pypi.org
Status: Not defined

CVE: CVE-2026-73325 (🔒)
GCVE (CVE): GCVE-0-2026-73325
GCVE (VulDB): GCVE-100-389090

Entryinfo

Created: 08/12/2026 18:33
Changes: 08/12/2026 18:33 (52)
Complete: 🔍
Cache ID: 216::103

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion

No comments yet. Languages: en.

Please log in to comment.

◂ PreviousOverviewNext ▸

Want to know what is going to be exploited?

We predict KEV entries!