CVE-2025-45146
ModelCache for LLM Deserialization Vulnerability
Description
ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/data_manager.py. This vulnerability allows attackers to execute arbitrary code via supplying crafted data.
INFO
Published Date :
Aug. 11, 2025, 4:15 p.m.
Last Modified :
Oct. 17, 2025, 6:06 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | CRITICAL | 134c704f-9b21-4f2e-91b3-4a467353bcc0 |
Solution
- Update the model cache to a version later than 0.2.0.
- Review and sanitize all input data before deserialization.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2025-45146.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2025-45146 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2025-45146
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2025-45146 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2025-45146 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Oct. 17, 2025
Action Type Old Value New Value Added CPE Configuration OR *cpe:2.3:a:codefuse:modelcache:*:*:*:*:*:*:*:* versions up to (including) 0.2.0 Added Reference Type MITRE: https://github.com/codefuse-ai/ModelCache/blob/e053e0d57b532d4ad9378d2f31bb85a009b77d64/modelcache/manager/data_manager.py#L84C1-L84C43 Types: Product Added Reference Type MITRE: https://github.com/codefuse-ai/ModelCache/blob/e053e0d57b532d4ad9378d2f31bb85a009b77d64/modelcache/manager/factory.py#L18C1-L18C71 Types: Product Added Reference Type MITRE: https://github.com/EDMPL/Vulnerability-Research/blob/main/CVE-2025-45146/README.md Types: Exploit, Third Party Advisory Added Reference Type MITRE: https://pytorch.org/docs/stable/generated/torch.load.html Types: Technical Description -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Aug. 11, 2025
Action Type Old Value New Value Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Added CWE CWE-502 -
New CVE Received by [email protected]
Aug. 11, 2025
Action Type Old Value New Value Added Description ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/data_manager.py. This vulnerability allows attackers to execute arbitrary code via supplying crafted data. Added Reference https://github.com/codefuse-ai/ModelCache/blob/e053e0d57b532d4ad9378d2f31bb85a009b77d64/modelcache/manager/data_manager.py#L84C1-L84C43 Added Reference https://github.com/codefuse-ai/ModelCache/blob/e053e0d57b532d4ad9378d2f31bb85a009b77d64/modelcache/manager/factory.py#L18C1-L18C71 Added Reference https://github.com/EDMPL/Vulnerability-Research/blob/main/CVE-2025-45146/README.md Added Reference https://pytorch.org/docs/stable/generated/torch.load.html