FKIE_CVE-2026-5497

Vulnerability from fkie_nvd - Published: 2026-06-11 10:16 - Updated: 2026-07-03 13:17
Severity
7.5 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Summary
vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.
References
security@huntr.devhttps://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395Patch
security@huntr.devhttps://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4Exploit, Third Party Advisory
0b0ca135-0b70-47e7-9f44-1890c2a1c46chttps://access.redhat.com/security/cve/CVE-2026-5497
0b0ca135-0b70-47e7-9f44-1890c2a1c46chttps://bugzilla.redhat.com/show_bug.cgi?id=2487813
134c704f-9b21-4f2e-91b3-4a467353bcc0https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4Exploit, Third Party Advisory
0b0ca135-0b70-47e7-9f44-1890c2a1c46chttps://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json
Impacted products
Vendor Product Version
vllm vllm *
To clipboard 

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "vllm-project/vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "lessThan": "0.19.0",
              "status": "affected",
              "version": "unspecified",
              "versionType": "custom"
            }
          ]
        }
      ],
      "source": "security@huntr.dev"
    },
    {
      "affectedData": [
        {
          "cpes": [
            "cpe:/a:redhat:ai_inference_server:3"
          ],
          "defaultStatus": "affected",
          "product": "Red Hat AI Inference Server",
          "vendor": "Red Hat"
        },
        {
          "cpes": [
            "cpe:/a:redhat:enterprise_linux_ai:3"
          ],
          "defaultStatus": "affected",
          "product": "Red Hat Enterprise Linux AI (RHEL AI) 3",
          "vendor": "Red Hat"
        },
        {
          "cpes": [
            "cpe:/a:redhat:openshift_ai"
          ],
          "defaultStatus": "affected",
          "product": "Red Hat OpenShift AI (RHOAI)",
          "vendor": "Red Hat"
        }
      ],
      "source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c"
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "06478E1E-65BE-4BC4-A65C-27E6B225DD10",
              "versionEndExcluding": "0.19.0",
              "versionStartIncluding": "0.8.0",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication."
    }
  ],
  "id": "CVE-2026-5497",
  "lastModified": "2026-07-03T13:17:30.490",
  "metrics": {
    "cvssMetricV30": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 7.5,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "NONE",
          "integrityImpact": "NONE",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
          "version": "3.0"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 3.6,
        "source": "security@huntr.dev",
        "type": "Secondary"
      }
    ],
    "cvssMetricV31": [
      {
        "cvssData": {
          "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"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 3.6,
        "source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-5497",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-06-11T14:01:03.081885Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-06-11T10:16:21.903",
  "references": [
    {
      "source": "security@huntr.dev",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395"
    },
    {
      "source": "security@huntr.dev",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ],
      "url": "https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4"
    },
    {
      "source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c",
      "url": "https://access.redhat.com/security/cve/CVE-2026-5497"
    },
    {
      "source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c",
      "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2487813"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ],
      "url": "https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4"
    },
    {
      "source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json"
    }
  ],
  "sourceIdentifier": "security@huntr.dev",
  "vulnStatus": "Modified",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-400"
        }
      ],
      "source": "security@huntr.dev",
      "type": "Secondary"
    },
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-770"
        }
      ],
      "source": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c",
      "type": "Secondary"
    }
  ]
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

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.