CVE-2025-23320

NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might lead to information disclosure.

CVSS v3 7.5 HIGH

7.5^/10

CVSS v3 : HIGH

Vector :

Exploitability : 3.9 / Impact : 3.6

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact NONE

Availability Impact NONE

Scope UNCHANGED

References

Link	Resource
https://nvd.nist.gov/vuln/detail/CVE-2025-23320	US Government Resource
https://nvidia.custhelp.com/app/answers/detail/a_id/5687	Vendor Advisory
https://www.cve.org/CVERecord?id=CVE-2025-23320	Third Party Advisory

Configurations

Configuration 1 (hide)

AND

cpe:2.3:a:nvidia:triton_inference_server:*:*:*:*:*:*:*:*

OR	cpe:2.3:o:linux:linux_kernel:-:::::::*
	cpe:2.3:o:microsoft:windows:-:::::::*

History

No history.

Information

Published : 2025-08-06 13:15

Updated : 2025-08-12 16:34

NVD link : CVE-2025-23320

Mitre link : CVE-2025-23320

CVE.ORG link : CVE-2025-23320

JSON object : View

Products Affected

microsoft

windows

nvidia

triton_inference_server

linux

linux_kernel

CWE

CWE-209

Generation of Error Message Containing Sensitive Information

{"id": "CVE-2025-23320", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "[email protected]", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 7.5, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 3.6, "exploitabilityScore": 3.9}]}, "published": "2025-08-06T13:15:39.633", "references": [{"url": "https://nvd.nist.gov/vuln/detail/CVE-2025-23320", "tags": ["US Government Resource"], "source": "[email protected]"}, {"url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5687", "tags": ["Vendor Advisory"], "source": "[email protected]"}, {"url": "https://www.cve.org/CVERecord?id=CVE-2025-23320", "tags": ["Third Party Advisory"], "source": "[email protected]"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Primary", "source": "[email protected]", "description": [{"lang": "en", "value": "CWE-209"}]}], "descriptions": [{"lang": "en", "value": "NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might lead to information disclosure."}, {"lang": "es", "value": "NVIDIA Triton Inference Server para Windows y Linux contiene una vulnerabilidad en el backend de Python, donde un atacante podr\u00eda sobrepasar el l\u00edmite de memoria compartida al enviar una solicitud muy grande. Explotar esta vulnerabilidad podr\u00eda resultar en la divulgaci\u00f3n de informaci\u00f3n."}], "lastModified": "2025-08-12T16:34:52.427", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:nvidia:triton_inference_server:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "2168003B-4C9F-4733-89F5-EA17B1228F95", "versionEndExcluding": "25.07"}], "operator": "OR"}, {"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:o:linux:linux_kernel:-:*:*:*:*:*:*:*", "vulnerable": false, "matchCriteriaId": "703AF700-7A70-47E2-BC3A-7FD03B3CA9C1"}, {"criteria": "cpe:2.3:o:microsoft:windows:-:*:*:*:*:*:*:*", "vulnerable": false, "matchCriteriaId": "A2572D17-1DE6-457B-99CC-64AFD54487EA"}], "operator": "OR"}], "operator": "AND"}], "sourceIdentifier": "[email protected]"}