CVE-2026-5497 (GCVE-0-2026-5497)

Vulnerability from cvelistv5 – Published: 2026-06-11 08:31 – Updated: 2026-06-11 14:01
VLAI
Title
Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm
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.
Severity
7.5 (High)
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
SSVC
Exploitation: poc Automatable: yes Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
  • CWE-400 - Uncontrolled Resource Consumption
Assigner
References
Impacted products
Vendor Product Version
vllm-project vllm-project/vllm Affected: unspecified , < 0.19.0 (custom)
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-5497",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-06-11T14:01:03.081885Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-06-11T14:01:07.379Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm-project/vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "lessThan": "0.19.0",
              "status": "affected",
              "version": "unspecified",
              "versionType": "custom"
            }
          ]
        }
      ],
      "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."
        }
      ],
      "metrics": [
        {
          "cvssV3_0": {
            "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"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-400",
              "description": "CWE-400 Uncontrolled Resource Consumption",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-06-11T08:31:18.953Z",
        "orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
        "shortName": "@huntr_ai"
      },
      "references": [
        {
          "url": "https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4"
        },
        {
          "url": "https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395"
        }
      ],
      "source": {
        "advisory": "7bd92629-b396-4449-8f88-6c0092530eb4",
        "discovery": "EXTERNAL"
      },
      "title": "Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
    "assignerShortName": "@huntr_ai",
    "cveId": "CVE-2026-5497",
    "datePublished": "2026-06-11T08:31:18.953Z",
    "dateReserved": "2026-04-03T14:41:01.113Z",
    "dateUpdated": "2026-06-11T14:01:07.379Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-5497",
      "date": "2026-06-11",
      "epss": "0.00077",
      "percentile": "0.23122"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-5497\",\"sourceIdentifier\":\"security@huntr.dev\",\"published\":\"2026-06-11T10:16:21.903\",\"lastModified\":\"2026-06-11T15:37:21.933\",\"vulnStatus\":\"Awaiting Analysis\",\"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.\"}],\"metrics\":{\"cvssMetricV30\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.0\",\"vectorString\":\"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H\",\"baseScore\":7.5,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"NONE\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":3.6}]},\"weaknesses\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-400\"}]}],\"references\":[{\"url\":\"https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395\",\"source\":\"security@huntr.dev\"},{\"url\":\"https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4\",\"source\":\"security@huntr.dev\"},{\"url\":\"https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-5497\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-06-11T14:01:03.081885Z\"}}}], \"references\": [{\"url\": \"https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-06-11T14:00:30.608Z\"}}], \"cna\": {\"title\": \"Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm\", \"source\": {\"advisory\": \"7bd92629-b396-4449-8f88-6c0092530eb4\", \"discovery\": \"EXTERNAL\"}, \"metrics\": [{\"cvssV3_0\": {\"scope\": \"UNCHANGED\", \"version\": \"3.0\", \"baseScore\": 7.5, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"NONE\"}}], \"affected\": [{\"vendor\": \"vllm-project\", \"product\": \"vllm-project/vllm\", \"versions\": [{\"status\": \"affected\", \"version\": \"unspecified\", \"lessThan\": \"0.19.0\", \"versionType\": \"custom\"}]}], \"references\": [{\"url\": \"https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4\"}, {\"url\": \"https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395\"}], \"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.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-400\", \"description\": \"CWE-400 Uncontrolled Resource Consumption\"}]}], \"providerMetadata\": {\"orgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"shortName\": \"@huntr_ai\", \"dateUpdated\": \"2026-06-11T08:31:18.953Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-5497\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-06-11T14:01:07.379Z\", \"dateReserved\": \"2026-04-03T14:41:01.113Z\", \"assignerOrgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"datePublished\": \"2026-06-11T08:31:18.953Z\", \"assignerShortName\": \"@huntr_ai\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


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.