Vulnerability-Lookup

CNVD-2025-22626

Vulnerability from cnvd - Published: 2025-09-22

Title

NVIDIA Triton Inference Server操作系统命令注入漏洞

Description

NVIDIA Triton Inference Server是美国英伟达（NVIDIA）公司的一款开源软件，有助于标准化模型部署并在生产中提供快速且可扩展的AI。 NVIDIA Triton Inference Server存在操作系统命令注入漏洞，该漏洞源于Python后端未正确处理模型控制API中的model name参数，攻击者可利用该漏洞可能导致远程代码执行、拒绝服务、信息泄露和数据篡改。

Severity

高

Patch Name

NVIDIA Triton Inference Server操作系统命令注入漏洞的补丁

Patch Description

Formal description

厂商已发布了漏洞修复程序，请及时关注更新： https://nvidia.custhelp.com/app/answers/detail/a_id/5691

Reference

https://nvd.nist.gov/vuln/detail/CVE-2025-23316

Impacted products

Name
NVIDIA Triton Inference Server <25.08

Show details on source website

JSON

To clipboard

{
  "cves": {
    "cve": {
      "cveNumber": "CVE-2025-23316",
      "cveUrl": "https://nvd.nist.gov/vuln/detail/CVE-2025-23316"
    }
  },
  "description": "NVIDIA Triton Inference Server\u662f\u7f8e\u56fd\u82f1\u4f1f\u8fbe\uff08NVIDIA\uff09\u516c\u53f8\u7684\u4e00\u6b3e\u5f00\u6e90\u8f6f\u4ef6\uff0c\u6709\u52a9\u4e8e\u6807\u51c6\u5316\u6a21\u578b\u90e8\u7f72\u5e76\u5728\u751f\u4ea7\u4e2d\u63d0\u4f9b\u5feb\u901f\u4e14\u53ef\u6269\u5c55\u7684AI\u3002\n\nNVIDIA Triton Inference Server\u5b58\u5728\u64cd\u4f5c\u7cfb\u7edf\u547d\u4ee4\u6ce8\u5165\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8ePython\u540e\u7aef\u672a\u6b63\u786e\u5904\u7406\u6a21\u578b\u63a7\u5236API\u4e2d\u7684model name\u53c2\u6570\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u53ef\u80fd\u5bfc\u81f4\u8fdc\u7a0b\u4ee3\u7801\u6267\u884c\u3001\u62d2\u7edd\u670d\u52a1\u3001\u4fe1\u606f\u6cc4\u9732\u548c\u6570\u636e\u7be1\u6539\u3002",
  "formalWay": "\u5382\u5546\u5df2\u53d1\u5e03\u4e86\u6f0f\u6d1e\u4fee\u590d\u7a0b\u5e8f\uff0c\u8bf7\u53ca\u65f6\u5173\u6ce8\u66f4\u65b0\uff1a\r\nhttps://nvidia.custhelp.com/app/answers/detail/a_id/5691",
  "isEvent": "\u901a\u7528\u8f6f\u786c\u4ef6\u6f0f\u6d1e",
  "number": "CNVD-2025-22626",
  "openTime": "2025-09-22",
  "patchDescription": "NVIDIA Triton Inference Server\u662f\u7f8e\u56fd\u82f1\u4f1f\u8fbe\uff08NVIDIA\uff09\u516c\u53f8\u7684\u4e00\u6b3e\u5f00\u6e90\u8f6f\u4ef6\uff0c\u6709\u52a9\u4e8e\u6807\u51c6\u5316\u6a21\u578b\u90e8\u7f72\u5e76\u5728\u751f\u4ea7\u4e2d\u63d0\u4f9b\u5feb\u901f\u4e14\u53ef\u6269\u5c55\u7684AI\u3002\r\n\r\nNVIDIA Triton Inference Server\u5b58\u5728\u64cd\u4f5c\u7cfb\u7edf\u547d\u4ee4\u6ce8\u5165\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8ePython\u540e\u7aef\u672a\u6b63\u786e\u5904\u7406\u6a21\u578b\u63a7\u5236API\u4e2d\u7684model name\u53c2\u6570\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u53ef\u80fd\u5bfc\u81f4\u8fdc\u7a0b\u4ee3\u7801\u6267\u884c\u3001\u62d2\u7edd\u670d\u52a1\u3001\u4fe1\u606f\u6cc4\u9732\u548c\u6570\u636e\u7be1\u6539\u3002\u76ee\u524d\uff0c\u4f9b\u5e94\u5546\u53d1\u5e03\u4e86\u5b89\u5168\u516c\u544a\u53ca\u76f8\u5173\u8865\u4e01\u4fe1\u606f\uff0c\u4fee\u590d\u4e86\u6b64\u6f0f\u6d1e\u3002",
  "patchName": "NVIDIA Triton Inference Server\u64cd\u4f5c\u7cfb\u7edf\u547d\u4ee4\u6ce8\u5165\u6f0f\u6d1e\u7684\u8865\u4e01",
  "products": {
    "product": "NVIDIA Triton Inference Server \u003c25.08"
  },
  "referenceLink": "https://nvd.nist.gov/vuln/detail/CVE-2025-23316",
  "serverity": "\u9ad8",
  "submitTime": "2025-09-19",
  "title": "NVIDIA Triton Inference Server\u64cd\u4f5c\u7cfb\u7edf\u547d\u4ee4\u6ce8\u5165\u6f0f\u6d1e"
}

CVE-2025-23316 (GCVE-0-2025-23316)

Vulnerability from cvelistv5 – Published: 2025-09-17 21:58 – Updated: 2025-09-18 14:03

Summary

NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause a remote code execution by manipulating the model name parameter in the model control APIs. A successful exploit of this vulnerability might lead to remote code execution, denial of service, information disclosure, and data tampering.

Severity

9.8 (Critical)


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

SSVC

Exploitation: none Automatable: yes Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2025-09-18 14:01 UTC

CWE

CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

Assigner

nvidia mitre root

References

1 reference

URL	Tags
https://nvidia.custhelp.com/app/answers/detail/a_…

Impacted products

1 product

Vendor	Product	Version
NVIDIA	Triton Inference Server	Affected: All versions prior to 25.08

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-23316",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-09-18T14:01:46.640784Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-09-18T14:03:58.291Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "platforms": [
            "Windows",
            "Linux"
          ],
          "product": "Triton Inference Server",
          "vendor": "NVIDIA",
          "versions": [
            {
              "status": "affected",
              "version": "All versions prior to 25.08"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "\u003cspan style=\"background-color: rgb(255, 255, 255);\"\u003eNVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause a remote code execution by manipulating the model name parameter in the model control APIs. A successful exploit of this vulnerability might lead to remote code execution, denial of service, information disclosure, and data tampering.\u003c/span\u003e"
            }
          ],
          "value": "NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause a remote code execution by manipulating the model name parameter in the model control APIs. A successful exploit of this vulnerability might lead to remote code execution, denial of service, information disclosure, and data tampering."
        }
      ],
      "impacts": [
        {
          "descriptions": [
            {
              "lang": "en",
              "value": "Code execution, denial of service, information disclosure, data tampering"
            }
          ]
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9.8,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-78",
              "description": "CWE-78 Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-09-17T21:58:15.643Z",
        "orgId": "9576f279-3576-44b5-a4af-b9a8644b2de6",
        "shortName": "nvidia"
      },
      "references": [
        {
          "url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5691"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "x_generator": {
        "engine": "Vulnogram 0.2.0"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "9576f279-3576-44b5-a4af-b9a8644b2de6",
    "assignerShortName": "nvidia",
    "cveId": "CVE-2025-23316",
    "datePublished": "2025-09-17T21:58:15.643Z",
    "dateReserved": "2025-01-14T01:06:28.098Z",
    "dateUpdated": "2025-09-18T14:03:58.291Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Detection rules are retrieved from Rulezet.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.