CVE-2026-22778 (GCVE-0-2026-22778)

Vulnerability from cvelistv5 – Published: 2026-02-02 21:09 – Updated: 2026-02-03 15:42
VLAI?
Title
vLLM leaks a heap address when PIL throws an error
Summary
vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.
CWE
  • CWE-532 - Insertion of Sensitive Information into Log File
Assigner
Impacted products
Vendor Product Version
vllm-project vllm Affected: >= 0.8.3, < 0.14.1
Create a notification for this product.
Show details on NVD website

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-22778",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-02-03T15:40:34.684022Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-02-03T15:42:57.155Z",
          "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= 0.8.3, \u003c 0.14.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM\u0027s multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1."
        }
      ],
      "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"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-532",
              "description": "CWE-532: Insertion of Sensitive Information into Log File",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-02-02T21:09:53.265Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/31987",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/31987"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/32319",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/32319"
        },
        {
          "name": "https://github.com/vllm-project/vllm/releases/tag/v0.14.1",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/releases/tag/v0.14.1"
        }
      ],
      "source": {
        "advisory": "GHSA-4r2x-xpjr-7cvv",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM leaks a heap address when PIL throws an error"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-22778",
    "datePublished": "2026-02-02T21:09:53.265Z",
    "dateReserved": "2026-01-09T18:27:19.388Z",
    "dateUpdated": "2026-02-03T15:42:57.155Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-22778\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-02-02T23:16:06.700\",\"lastModified\":\"2026-02-23T18:19:12.450\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM\u0027s multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.\"},{\"lang\":\"es\",\"value\":\"vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLM). Desde la versi\u00f3n 0.8.3 hasta antes de la 0.14.1, cuando se env\u00eda una imagen inv\u00e1lida al endpoint multimodal de vLLM, PIL lanza un error. vLLM devuelve este error al cliente, filtrando una direcci\u00f3n de mont\u00edculo. Con esta fuga, reducimos ASLR de 4 mil millones de intentos a ~8 intentos. Esta vulnerabilidad puede encadenarse a un desbordamiento de mont\u00edculo con el decodificador JPEG2000 en OpenCV/FFmpeg para lograr ejecuci\u00f3n remota de c\u00f3digo. Esta vulnerabilidad est\u00e1 corregida en la versi\u00f3n 0.14.1.\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":9.8,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":5.9}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-532\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*\",\"versionStartIncluding\":\"0.8.3\",\"versionEndExcluding\":\"0.14.1\",\"matchCriteriaId\":\"6EBA2094-B756-41D7-A899-8C028DF95FF4\"}]}]}],\"references\":[{\"url\":\"https://github.com/vllm-project/vllm/pull/31987\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Issue Tracking\",\"Patch\"]},{\"url\":\"https://github.com/vllm-project/vllm/pull/32319\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Issue Tracking\",\"Patch\"]},{\"url\":\"https://github.com/vllm-project/vllm/releases/tag/v0.14.1\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Release Notes\"]},{\"url\":\"https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Vendor Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"cna\": {\"title\": \"vLLM leaks a heap address when PIL throws an error\", \"source\": {\"advisory\": \"GHSA-4r2x-xpjr-7cvv\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 9.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"vllm-project\", \"product\": \"vllm\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= 0.8.3, \u003c 0.14.1\"}]}], \"references\": [{\"url\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv\", \"name\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/vllm-project/vllm/pull/31987\", \"name\": \"https://github.com/vllm-project/vllm/pull/31987\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/vllm-project/vllm/pull/32319\", \"name\": \"https://github.com/vllm-project/vllm/pull/32319\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/vllm-project/vllm/releases/tag/v0.14.1\", \"name\": \"https://github.com/vllm-project/vllm/releases/tag/v0.14.1\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM\u0027s multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-532\", \"description\": \"CWE-532: Insertion of Sensitive Information into Log File\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-02-02T21:09:53.265Z\"}}, \"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-22778\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-02-03T15:40:34.684022Z\"}}}], \"providerMetadata\": {\"shortName\": \"CISA-ADP\", \"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"dateUpdated\": \"2026-02-03T15:42:51.507Z\"}}]}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-22778\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-02-02T21:09:53.265Z\", \"dateReserved\": \"2026-01-09T18:27:19.388Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-02-02T21:09:53.265Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

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.


Loading…

Detection rules are retrieved from Rulezet.

Loading…

Loading…