github - ghsa-rxc4-3w6r-4v47

GHSA-RXC4-3W6R-4V47

Vulnerability from github – Published: 2025-08-21 14:24 – Updated: 2025-08-21 15:42

Summary

vllm API endpoints vulnerable to Denial of Service Attacks

Details

Summary

A Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user.

Details

The vulnerability leverages the abuse of HTTP headers. By setting a header such as X-Forwarded-For to a very large value like ("A" * 5_800_000_000), the server's HTTP parser or application logic may attempt to load the entire request into memory, overwhelming system resources.

Impact

What kind of vulnerability is it? Who is impacted? Type of vulnerability: Denial of Service (DoS)

Resolution

Upgrade to a version of vLLM that includes appropriate HTTP limits by deafult, or use a proxy in front of vLLM which provides protection against this issue.

Severity ?

7.5 (High)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.1.0"
            },
            {
              "fixed": "0.10.1.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-48956"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-400"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-08-21T14:24:16Z",
    "nvd_published_at": "2025-08-21T15:15:32Z",
    "severity": "HIGH"
  },
  "details": "### Summary\nA Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user.\n\n### Details\nThe vulnerability leverages the abuse of HTTP headers. By setting a header such as `X-Forwarded-For` to a very large value like `(\"A\" * 5_800_000_000)`, the server\u0027s HTTP parser or application logic may attempt to load the entire request into memory, overwhelming system resources.\n\n### Impact\n_What kind of vulnerability is it? Who is impacted?_\nType of vulnerability: Denial of Service (DoS)\n\n### Resolution\nUpgrade to a version of vLLM that includes appropriate HTTP limits by deafult, or use a proxy in front of vLLM which provides protection against this issue.",
  "id": "GHSA-rxc4-3w6r-4v47",
  "modified": "2025-08-21T15:42:03Z",
  "published": "2025-08-21T14:24:16Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-48956"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/23267"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vllm API endpoints vulnerable to Denial of Service Attacks"
}

CVE-2025-48956 (GCVE-0-2025-48956)

Vulnerability from cvelistv5 – Published: 2025-08-21 14:41 – Updated: 2025-08-21 15:02

Summary

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.

Severity ?

7.5 (High)


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

CWE

CWE-400 - Uncontrolled Resource Consumption

Assigner

GitHub_M

References

URL

Tags

	https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
	https://github.com/vllm-project/vllm/pull/23267	x_refsource_MISC
	https://github.com/vllm-project/vllm/commit/d8b73…	x_refsource_MISC

Impacted products

	Vendor	Product	Version
	vllm-project	vllm	Affected: >= 0.1.0, < 0.10.1.1

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-48956",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-08-21T15:01:51.159829Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-08-21T15:02:09.023Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.1.0, \u003c 0.10.1.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 7.5,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-400",
              "description": "CWE-400: Uncontrolled Resource Consumption",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-08-21T14:41:03.889Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/23267",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/23267"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944"
        }
      ],
      "source": {
        "advisory": "GHSA-rxc4-3w6r-4v47",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM API endpoints vulnerable to Denial of Service Attacks"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-48956",
    "datePublished": "2025-08-21T14:41:03.889Z",
    "dateReserved": "2025-05-28T18:49:07.585Z",
    "dateUpdated": "2025-08-21T15:02:09.023Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

Sightings

Author	Source	Type	Date

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.

Action not permitted

GHSA-RXC4-3W6R-4V47

Summary

Details

Impact

Resolution

CVE-2025-48956 (GCVE-0-2025-48956)

Tags

Sightings

Nomenclature