Zetlyn
GitHubGet started

vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.

zetlyn/cve-nvd vulnerability cve CVE-2026-100650 known 2026-09-26

https://nvd.nist.gov/vuln/detail/CVE-2026-100650

Properties

cvss6.5
receipt
Source
NVD
Its words
6.5
Read by
field:cve.metrics.cvssMetricV31[].cvssData.baseScore
Said since
2026-09-29 09:39 UTC
Last answered
2026-10-05 12:24 UTC
Original
open at the source
What the source handed over
{
  "cve": {
    "affected": [
      {
        "affectedData": [
          {
            "defaultStatus": "unaffected",
            "packageURL": "pkg:pypi/vllm",
            "product": "vllm",
            "vendor": "vllm-project",
            "versions": [
              {
                "lessThan": "0.29.0",
                "status": "affected",
                "version": "0",
                "versionType": "semver"
              },
              {
                "status": "unaffected",
                "version": "0.29.0",
                "versionType": "semver"
              }
            ]
          }
        ],
        "source": "disclosure@vulncheck.com"
      }
    ],
    "cveTags": [],
    "descriptions": [
      {
        "lang": "en",
        "value": "vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact."
      }
    ],
    "id": "CVE-2026-100650",
    "lastModified": "2026-09-30T15:22:10.603",
    "metrics": {
      "cvssMetricV31": [
        {
          "cvssData": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 6.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
            "version": "3.1"
          },
          "exploitabilityScore": 2.8,
          "impactScore": 3.6,
          "source": "disclosure@vulncheck.com",
          "type": "Secondary"
        }
      ],
      "cvssMetricV40": [
        {
          "cvssData": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "availabilityRequirement": "NOT_DEFINED",
            "baseScore": 7.1,
            "baseSeverity": "HIGH",
            "confidentialityRequirement": "NOT_DEFINED",
            "exploitMaturity": "NOT_DEFINED",
            "integrityRequirement": "NOT_DEFINED",
            "modifiedAttackComplexity": "NOT_DEFINED",
            "modifiedAttackRequirements": "NOT_DEFINED",
            "modifiedAttackVector": "NOT_DEFINED",
            "modifiedPrivilegesRequired": "NOT_DEFINED",
            "modifiedSubAvailabilityImpact": "NOT_DEFINED",
            "modifiedSubConfidentialityImpact": "NOT_DEFINED",
            "modifiedSubIntegrityImpact": "NOT_DEFINED",
            "modifiedUserInteraction": "NOT_DEFINED",
            "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
            "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
            "modifiedVulnIntegrityImpact": "NOT_DEFINED",
            "privilegesRequired": "LOW",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "source": "disclosure@vulncheck.com",
          "type": "Secondary"
        }
      ],
      "ssvcV203": [
        {
          "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "ssvcData": {
            "id": "CVE-2026-100650",
            "options": [
              {
                "exploitation": "poc"
              },
              {
                "automatable": "no"
              },
              {
                "technicalImpact": "partial"
              }
            ],
            "role": "CISA Coordinator",
            "timestamp": "2026-09-30T14:49:40.322864Z",
            "version": "2.0.3"
          }
        }
      ]
    },
    "published": "2026-09-26T14:16:47.523",
    "references": [
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34"
      },
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"
      },
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization"
      },
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"
      }
    ],
    "sourceIdentifier": "disclosure@vulncheck.com",
    "vulnStatus": "Undergoing Analysis",
    "weaknesses": [
      {
        "description": [
          {
            "lang": "en",
            "value": "CWE-400"
          }
        ],
        "source": "disclosure@vulncheck.com",
        "type": "Secondary"
      }
    ]
  }
}
productvllm
receipt
Source
NVD
Its words
vllm
Read by
field:cve.affected[].affectedData[].product
Said since
2026-09-29 17:49 UTC
Last answered
2026-10-05 12:24 UTC
Original
open at the source
2026-09-29 17:49 UTCvllm
2026-09-29 09:39 UTC—
What the source handed over
{
  "cve": {
    "affected": [
      {
        "affectedData": [
          {
            "defaultStatus": "unaffected",
            "packageURL": "pkg:pypi/vllm",
            "product": "vllm",
            "vendor": "vllm-project",
            "versions": [
              {
                "lessThan": "0.29.0",
                "status": "affected",
                "version": "0",
                "versionType": "semver"
              },
              {
                "status": "unaffected",
                "version": "0.29.0",
                "versionType": "semver"
              }
            ]
          }
        ],
        "source": "disclosure@vulncheck.com"
      }
    ],
    "cveTags": [],
    "descriptions": [
      {
        "lang": "en",
        "value": "vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact."
      }
    ],
    "id": "CVE-2026-100650",
    "lastModified": "2026-09-30T15:22:10.603",
    "metrics": {
      "cvssMetricV31": [
        {
          "cvssData": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 6.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
            "version": "3.1"
          },
          "exploitabilityScore": 2.8,
          "impactScore": 3.6,
          "source": "disclosure@vulncheck.com",
          "type": "Secondary"
        }
      ],
      "cvssMetricV40": [
        {
          "cvssData": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "availabilityRequirement": "NOT_DEFINED",
            "baseScore": 7.1,
            "baseSeverity": "HIGH",
            "confidentialityRequirement": "NOT_DEFINED",
            "exploitMaturity": "NOT_DEFINED",
            "integrityRequirement": "NOT_DEFINED",
            "modifiedAttackComplexity": "NOT_DEFINED",
            "modifiedAttackRequirements": "NOT_DEFINED",
            "modifiedAttackVector": "NOT_DEFINED",
            "modifiedPrivilegesRequired": "NOT_DEFINED",
            "modifiedSubAvailabilityImpact": "NOT_DEFINED",
            "modifiedSubConfidentialityImpact": "NOT_DEFINED",
            "modifiedSubIntegrityImpact": "NOT_DEFINED",
            "modifiedUserInteraction": "NOT_DEFINED",
            "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
            "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
            "modifiedVulnIntegrityImpact": "NOT_DEFINED",
            "privilegesRequired": "LOW",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "source": "disclosure@vulncheck.com",
          "type": "Secondary"
        }
      ],
      "ssvcV203": [
        {
          "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "ssvcData": {
            "id": "CVE-2026-100650",
            "options": [
              {
                "exploitation": "poc"
              },
              {
                "automatable": "no"
              },
              {
                "technicalImpact": "partial"
              }
            ],
            "role": "CISA Coordinator",
            "timestamp": "2026-09-30T14:49:40.322864Z",
            "version": "2.0.3"
          }
        }
      ]
    },
    "published": "2026-09-26T14:16:47.523",
    "references": [
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34"
      },
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"
      },
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization"
      },
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"
      }
    ],
    "sourceIdentifier": "disclosure@vulncheck.com",
    "vulnStatus": "Undergoing Analysis",
    "weaknesses": [
      {
        "description": [
          {
            "lang": "en",
            "value": "CWE-400"
          }
        ],
        "source": "disclosure@vulncheck.com",
        "type": "Secondary"
      }
    ]
  }
}
statusUndergoing Analysis
receipt
Source
NVD
Its words
Undergoing Analysis
Read by
field:cve.vulnStatus
Said since
2026-10-02 12:00 UTC
Last answered
2026-10-05 12:24 UTC
Original
open at the source
2026-10-02 12:00 UTCUndergoing Analysis
2026-09-29 09:39 UTCAwaiting Analysis
What the source handed over
{
  "cve": {
    "affected": [
      {
        "affectedData": [
          {
            "defaultStatus": "unaffected",
            "packageURL": "pkg:pypi/vllm",
            "product": "vllm",
            "vendor": "vllm-project",
            "versions": [
              {
                "lessThan": "0.29.0",
                "status": "affected",
                "version": "0",
                "versionType": "semver"
              },
              {
                "status": "unaffected",
                "version": "0.29.0",
                "versionType": "semver"
              }
            ]
          }
        ],
        "source": "disclosure@vulncheck.com"
      }
    ],
    "cveTags": [],
    "descriptions": [
      {
        "lang": "en",
        "value": "vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact."
      }
    ],
    "id": "CVE-2026-100650",
    "lastModified": "2026-09-30T15:22:10.603",
    "metrics": {
      "cvssMetricV31": [
        {
          "cvssData": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 6.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
            "version": "3.1"
          },
          "exploitabilityScore": 2.8,
          "impactScore": 3.6,
          "source": "disclosure@vulncheck.com",
          "type": "Secondary"
        }
      ],
      "cvssMetricV40": [
        {
          "cvssData": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "availabilityRequirement": "NOT_DEFINED",
            "baseScore": 7.1,
            "baseSeverity": "HIGH",
            "confidentialityRequirement": "NOT_DEFINED",
            "exploitMaturity": "NOT_DEFINED",
            "integrityRequirement": "NOT_DEFINED",
            "modifiedAttackComplexity": "NOT_DEFINED",
            "modifiedAttackRequirements": "NOT_DEFINED",
            "modifiedAttackVector": "NOT_DEFINED",
            "modifiedPrivilegesRequired": "NOT_DEFINED",
            "modifiedSubAvailabilityImpact": "NOT_DEFINED",
            "modifiedSubConfidentialityImpact": "NOT_DEFINED",
            "modifiedSubIntegrityImpact": "NOT_DEFINED",
            "modifiedUserInteraction": "NOT_DEFINED",
            "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
            "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
            "modifiedVulnIntegrityImpact": "NOT_DEFINED",
            "privilegesRequired": "LOW",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "source": "disclosure@vulncheck.com",
          "type": "Secondary"
        }
      ],
      "ssvcV203": [
        {
          "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "ssvcData": {
            "id": "CVE-2026-100650",
            "options": [
              {
                "exploitation": "poc"
              },
              {
                "automatable": "no"
              },
              {
                "technicalImpact": "partial"
              }
            ],
            "role": "CISA Coordinator",
            "timestamp": "2026-09-30T14:49:40.322864Z",
            "version": "2.0.3"
          }
        }
      ]
    },
    "published": "2026-09-26T14:16:47.523",
    "references": [
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34"
      },
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"
      },
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization"
      },
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"
      }
    ],
    "sourceIdentifier": "disclosure@vulncheck.com",
    "vulnStatus": "Undergoing Analysis",
    "weaknesses": [
      {
        "description": [
          {
            "lang": "en",
            "value": "CWE-400"
          }
        ],
        "source": "disclosure@vulncheck.com",
        "type": "Secondary"
      }
    ]
  }
}
vendorvllm-project
receipt
Source
NVD
Its words
vllm-project
Read by
field:cve.affected[].affectedData[].vendor
Said since
2026-09-29 17:49 UTC
Last answered
2026-10-05 12:24 UTC
Original
open at the source
2026-09-29 17:49 UTCvllm-project
2026-09-29 09:39 UTC—
What the source handed over
{
  "cve": {
    "affected": [
      {
        "affectedData": [
          {
            "defaultStatus": "unaffected",
            "packageURL": "pkg:pypi/vllm",
            "product": "vllm",
            "vendor": "vllm-project",
            "versions": [
              {
                "lessThan": "0.29.0",
                "status": "affected",
                "version": "0",
                "versionType": "semver"
              },
              {
                "status": "unaffected",
                "version": "0.29.0",
                "versionType": "semver"
              }
            ]
          }
        ],
        "source": "disclosure@vulncheck.com"
      }
    ],
    "cveTags": [],
    "descriptions": [
      {
        "lang": "en",
        "value": "vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact."
      }
    ],
    "id": "CVE-2026-100650",
    "lastModified": "2026-09-30T15:22:10.603",
    "metrics": {
      "cvssMetricV31": [
        {
          "cvssData": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 6.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
            "version": "3.1"
          },
          "exploitabilityScore": 2.8,
          "impactScore": 3.6,
          "source": "disclosure@vulncheck.com",
          "type": "Secondary"
        }
      ],
      "cvssMetricV40": [
        {
          "cvssData": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "availabilityRequirement": "NOT_DEFINED",
            "baseScore": 7.1,
            "baseSeverity": "HIGH",
            "confidentialityRequirement": "NOT_DEFINED",
            "exploitMaturity": "NOT_DEFINED",
            "integrityRequirement": "NOT_DEFINED",
            "modifiedAttackComplexity": "NOT_DEFINED",
            "modifiedAttackRequirements": "NOT_DEFINED",
            "modifiedAttackVector": "NOT_DEFINED",
            "modifiedPrivilegesRequired": "NOT_DEFINED",
            "modifiedSubAvailabilityImpact": "NOT_DEFINED",
            "modifiedSubConfidentialityImpact": "NOT_DEFINED",
            "modifiedSubIntegrityImpact": "NOT_DEFINED",
            "modifiedUserInteraction": "NOT_DEFINED",
            "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
            "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
            "modifiedVulnIntegrityImpact": "NOT_DEFINED",
            "privilegesRequired": "LOW",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "NONE",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "source": "disclosure@vulncheck.com",
          "type": "Secondary"
        }
      ],
      "ssvcV203": [
        {
          "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "ssvcData": {
            "id": "CVE-2026-100650",
            "options": [
              {
                "exploitation": "poc"
              },
              {
                "automatable": "no"
              },
              {
                "technicalImpact": "partial"
              }
            ],
            "role": "CISA Coordinator",
            "timestamp": "2026-09-30T14:49:40.322864Z",
            "version": "2.0.3"
          }
        }
      ]
    },
    "published": "2026-09-26T14:16:47.523",
    "references": [
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34"
      },
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"
      },
      {
        "source": "disclosure@vulncheck.com",
        "url": "https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization"
      },
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"
      }
    ],
    "sourceIdentifier": "disclosure@vulncheck.com",
    "vulnStatus": "Undergoing Analysis",
    "weaknesses": [
      {
        "description": [
          {
            "lang": "en",
            "value": "CWE-400"
          }
        ],
        "source": "disclosure@vulncheck.com",
        "type": "Secondary"
      }
    ]
  }
}

Text

vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.