CVE-2025-9141 - Vulnerability Details - OpenCVE

A vulnerability was found in vLLM's Qwen3 Coder tool parser. Since this parser uses Python's eval() function, it poses a risk of arbitrary code execution. This vulnerability appears during the parameter conversion process when the parser attempts to handle complex data types.

No CVSS v4.0

Attack Vector Network

Attack Complexity Low

Privileges Required Low

Scope Unchanged

Confidentiality Impact High

Integrity Impact High

Availability Impact High

User Interaction None

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

No EPSS score available.

Key SSVC decision points have not yet been added.

No data.

No data.

No data.

No data.

Advisories

Source	ID	Title
EUVD	EUVD-2025-29456	vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder
Github GHSA	GHSA-79j6-g2m3-jgfw	vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

Fixes

Solution

No solution given by the vendor.

Workaround

No workaround given by the vendor.

References

Link	Providers
https://github.com/vllm-project/vllm/security/advisories/GHSA-79j6-g2m3-jgfw
https://nvd.nist.gov/vuln/detail/CVE-2025-9141
https://www.cve.org/CVERecord?id=CVE-2025-9141

History

Thu, 21 Aug 2025 12:15:00 +0000

Type	Values Removed	Values Added
Description		A vulnerability was found in vLLM's Qwen3 Coder tool parser. Since this parser uses Python's eval() function, it poses a risk of arbitrary code execution. This vulnerability appears during the parameter conversion process when the parser attempts to handle complex data types.
Title		vllm: quen3: RCE in vllm tool call parser for qwen3coder
Weaknesses		CWE-502
References		https://github.com/vllm-project/vllm/security/advisories/GHSA-79j6-g2m3-jgfw https://nvd.nist.gov/vuln/detail/CVE-2025-9141 https://www.cve.org/CVERecord?id=CVE-2025-9141
Metrics	threat_severity `None`	cvssV3_1 `{'score': 8.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H'}` threat_severity `Important`

MITRE

No data.

Vulnrichment

No data.

NVD

No data.

Redhat

Severity : Important

Publid Date: 2025-08-20T23:37:00Z

Links: CVE-2025-9141 - Bugzilla

OpenCVE Enrichment

No data.

{"bugzilla": {"description": "vllm: quen3: RCE in vllm tool call parser for qwen3coder", "id": "2389395", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2389395"}, "csaw": false, "cvss3": {"cvss3_base_score": "8.8", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H", "status": "draft"}, "cwe": "CWE-502", "details": ["A vulnerability was found in vLLM's Qwen3 Coder tool parser. Since this parser uses Python's eval() function, it poses a risk of arbitrary code execution. This vulnerability appears during the parameter conversion process when the parser attempts to handle complex data types."], "name": "CVE-2025-9141", "package_state": [{"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/deepseek-r1-0528-quantized-w4a16", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/gemma-3n-e4b-it", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/kimi-k2-instruct-quantized-w4a16", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/modelcar-deepseek-r1-0528-quantized-w4a16", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/modelcar-gemma-3n-e4b-it", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/modelcar-kimi-k2-instruct-quantized-w4a16", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/modelcar-qwen3-4b-quantized-w4a16", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/modelcar-smollm3-3b", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/qwen3-4b-quantized-w4a16", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}, {"cpe": "cpe:/a:redhat:enterprise_linux_ai:1", "fix_state": "Not affected", "package_name": "rhelai1/smollm3-3b", "product_name": "Red Hat Enterprise Linux AI (RHEL AI)"}], "public_date": "2025-08-20T23:37:00Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2025-9141\nhttps://nvd.nist.gov/vuln/detail/CVE-2025-9141\nhttps://github.com/vllm-project/vllm/security/advisories/GHSA-79j6-g2m3-jgfw"], "statement": "This vulnerability was discovered and fixed in the upstream qwen3 component. It never affected any Red Hat products.\nThe impact is Important as it could allow remote code execution. The precondition of an attacker needing valid login credentials, prevents it from being Critical.", "threat_severity": "Important"}