CVE-2025-9141: Vllm Remote Code Execution Vulnerability

HIGH
Advisory Identifier: GHSA-79j6-g2m3-jgfw
Share
CVSS 8.8
CWE-502
Published
Advisory Summary

CVE-2025-9141 is a HIGH (CVSS 8.8) remote code execution vulnerability (CWE-502: Deserialization of Untrusted Data) affecting Vllm libraries in the PyPI ecosystem. The issue involves vllm has remote code execution vulnerability in the tool call parser for qwen3-coder. Remediation is available by upgrading affected packages to version 0.10.1.1.

CVE-2025-9141 at a Glance

CVE Identifier CVE-2025-9141
GHSA Identifier GHSA-79j6-g2m3-jgfw
Severity HIGH
CVSS v3.1 Base Score 8.8
CWE Classification CWE-502: Deserialization of Untrusted Data
Affected Product Vllm
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 8.8

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required Low (PR:L)
User Interaction None (UI:N)
Scope Unchanged (S:U)
Confidentiality High (C:H)
Integrity High (I:H)
Availability High (A:H)

How to Fix CVE-2025-9141

To remediate this vulnerability, upgrade all affected Vllm dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

vllm fixed: 0.10.1.1 
pip install vllm>=0.10.1.1
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release: 

pip show vllm

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2025-9141, inspect your installed packages using pip:

pip show vllm

Analyze the terminal output to locate any version of Vllm in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 0.10.1.1), your application is affected.

Note: The pip show vllm command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-502: Deserialization of Untrusted Data, where the product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid. In Vllm, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

### Summary An unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. ### Details vLLM's [Qwen3 Coder tool parser](https://github.com/vllm-project/vllm/blob/main/vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py) contains a code execution path that uses Python's `eval()` function to parse tool call parameters. This occurs during the parameter conversion process when the parser attempts to handle unknown data types. This code path is reached when: 1. Tool calling is enabled (`--enable-auto-tool-choice`) 2. The qwen3_coder parser is specified (`--tool-call-parser qwen3_coder`) 3. The parameter type is not explicitly defined or recognized ### Impact Remote Code Execution via Python's `eval()` function.

CVE-2025-9141 Affected Vllm Versions

1 component(s)
Fixed Versions:
0.10.1.1
Product / Package Ecosystem Affected Versions Fixed Version
vllm
pypi/vllm
PyPI
≥ 0.10.0
< 0.10.1.1
0.10.1.1

References

Vllm Source Repository REPOSITORY
https://github.com/vllm-project/vllm/pull/21396
GitHub Advisory / Wiki ADVISORY
https://github.com/vllm-project/vllm/security/advisories/GHSA-79j6-g2m3-jgfw
Security Fix Commit FIX COMMIT
https://github.com/vllm-project/vllm/commit/4594fc3b281713bd3d7634405b4a1393af40d294
Vllm Source Repository REPOSITORY
https://github.com/vllm-project/vllm

Frequently Asked Questions

What is CVE-2025-9141?
CVE-2025-9141 is a security vulnerability in Vllm involving vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder under CWE-502: Deserialization of Untrusted Data.
Which Vllm versions are affected?
Affected versions include releases prior to 0.10.1.1 across affected packages: vllm.
What version fixes CVE-2025-9141?
Upgrading to 0.10.1.1 (or the latest patched release for your respective branch) resolves the vulnerability.
Is vllm affected?
Yes, vllm is affected in releases prior to 0.10.1.1. Upgrade your dependency to 0.10.1.1 or later.
What is the CVSS score of CVE-2025-9141?
CVE-2025-9141 has a CVSS v3.1 base score of 8.8 (HIGH) with vector string CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H.
What CWE is associated with CVE-2025-9141?
CVE-2025-9141 is classified under CWE-502: Deserialization of Untrusted Data (The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.).
How can I check PyPI dependencies for CVE-2025-9141?
Run the dependency tree command: 'pip show vllm'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
View Raw JSON 
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-79j6-g2m3-jgfw",
  "modified" : "2025-08-21T14:46:51Z",
  "published" : "2025-08-21T14:46:51Z",
  "aliases" : [ "CVE-2025-9141" ],
  "summary" : "vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder",
  "details" : "### Summary\nAn unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call.\n\n### Details\n vLLM's [Qwen3 Coder tool parser](https://github.com/vllm-project/vllm/blob/main/vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py) contains a code execution path that uses Python's `eval()` function to parse tool call parameters. This occurs during the parameter conversion process when the parser attempts to handle unknown data types.\n\nThis code path is reached when:\n1. Tool calling is enabled (`--enable-auto-tool-choice`)\n2. The qwen3_coder parser is specified (`--tool-call-parser qwen3_coder`)\n3. The parameter type is not explicitly defined or recognized\n\n### Impact\nRemote Code Execution via Python's `eval()` function.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "vllm"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0.10.0"
      }, {
        "fixed" : "0.10.1.1"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/security/advisories/GHSA-79j6-g2m3-jgfw"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/pull/21396"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/commit/4594fc3b281713bd3d7634405b4a1393af40d294"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/vllm-project/vllm"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-502" ],
    "severity" : "HIGH",
    "github_reviewed" : true,
    "github_reviewed_at" : "2025-08-21T14:46:51Z",
    "nvd_published_at" : null
  }
}