What is the CVSS score of CVE-2025-45146?

CVE-2025-45146 has a CVSS 3.1 base score of 9.8 (Critical). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.4%.

Which versions of Modelcache are affected by CVE-2025-45146?

Organizations using ModelCache for LLM through v0.2.0 face critical risk from CVE-2025-45146, a insecure deserialization vulnerability rated CVSS 9.8.

Is there a public PoC exploit available for CVE-2025-45146?

Yes, a public proof-of-concept exploit is available for CVE-2025-45146. Prioritise patching immediately. EPSS: 0.4%.

How to fix or mitigate CVE-2025-45146?

Within 24 hours: Identify all affected systems and apply vendor patches immediately. Restrict deserialization to trusted data sources and implement integrity checks.

Modelcache CVE-2025-45146

CRITICAL

Deserialization of Untrusted Data (CWE-502)

2025-08-11 cve@mitre.org

RCE Deserialization Modelcache

9.8

CVSS 3.1 · NVD

Severity by source

NVD PRIMARY

9.8 CRITICAL

AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Analysis Generated

Mar 28, 2026 - 19:06 vuln.today

PoC Detected

Oct 17, 2025 - 18:06 vuln.today

Public exploit code

CVE Published

Aug 11, 2025 - 16:15 nvd

CRITICAL 9.8

DescriptionCVE.org

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.

AnalysisAI

ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/data_manager.py. Rated critical severity (CVSS 9.8), this vulnerability is remotely exploitable, no authentication required, low attack complexity. Public exploit code available and no vendor patch available.

Technical ContextAI

This vulnerability is classified as Deserialization of Untrusted Data (CWE-502), which allows attackers to execute arbitrary code through malicious serialized objects. 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. Affected products include: Codefuse Modelcache.

RemediationAI

No vendor patch is available at time of analysis. Monitor vendor advisories for updates. Avoid deserializing untrusted data. Use safe serialization formats (JSON). Implement integrity checks and type allowlists.

CVE-2025-45146 vulnerability details – vuln.today

Back

Modelcache CVE-2025-45146

Severity by source

CVSS VectorNVD

Lifecycle Timeline

DescriptionCVE.org

AnalysisAI

Technical ContextAI

RemediationAI

Share

External POC / Exploit Code