GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

CVE-2026-44555 (GCVE-0-2026-44555)

Vulnerability from cvelistv5 – Published: 2026-05-15 19:48 – Updated: 2026-05-15 20:21
VLAI
Title
Open WebUI: Base Model Routing Bypasses Access Control via Model Chaining
Summary
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.0, Open WebUI supports model composition via base_model_id: a user-defined model (e.g., "Cheap Assistant") can reference an existing base model (e.g., "gpt-4-turbo-restricted") that provides the actual inference capability. When a user queries the composed model, the access control pipeline verifies the user has access to the composed model but never re-verifies access to the chained base model. Additionally, the model creation and import endpoints accept arbitrary base_model_id values without checking that the caller has access to that base model. Combined, this allows any user with the default model creation permission to create a model that chains to a restricted base model — and then invoke it, causing the server to dispatch the request to the restricted base model using the admin-configured API key. This vulnerability is fixed in 0.9.0.
Severity
7.6 (High)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L
SSVC
Exploitation: poc Automatable: no Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-05-15 20:21 UTC
CWE
Assigner
References
Impacted products
Vendor Product Version CPE status
open-webui open-webui Affected: < 0.9.0
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-44555",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-15T20:21:00.262151Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-15T20:21:22.063Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-9vvh-qmjx-p4q8"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "open-webui",
          "vendor": "open-webui",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.9.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.0, Open WebUI supports model composition via base_model_id: a user-defined model (e.g., \"Cheap Assistant\") can reference an existing base model (e.g., \"gpt-4-turbo-restricted\") that provides the actual inference capability. When a user queries the composed model, the access control pipeline verifies the user has access to the composed model but never re-verifies access to the chained base model. Additionally, the model creation and import endpoints accept arbitrary base_model_id values without checking that the caller has access to that base model. Combined, this allows any user with the default model creation permission to create a model that chains to a restricted base model \u2014 and then invoke it, causing the server to dispatch the request to the restricted base model using the admin-configured API key. This vulnerability is fixed in 0.9.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "LOW",
            "baseScore": 7.6,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "LOW",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-862",
              "description": "CWE-862: Missing Authorization",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-15T19:48:35.352Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/open-webui/open-webui/security/advisories/GHSA-9vvh-qmjx-p4q8",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-9vvh-qmjx-p4q8"
        }
      ],
      "source": {
        "advisory": "GHSA-9vvh-qmjx-p4q8",
        "discovery": "UNKNOWN"
      },
      "title": "Open WebUI: Base Model Routing Bypasses Access Control via Model Chaining"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-44555",
    "datePublished": "2026-05-15T19:48:35.352Z",
    "dateReserved": "2026-05-06T20:59:00.594Z",
    "dateUpdated": "2026-05-15T20:21:22.063Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-44555",
      "date": "2026-09-17",
      "epss": "0.00304",
      "percentile": "0.23164"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-44555\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-05-15T20:16:46.967\",\"lastModified\":\"2026-06-17T10:50:47.120\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.0, Open WebUI supports model composition via base_model_id: a user-defined model (e.g., \\\"Cheap Assistant\\\") can reference an existing base model (e.g., \\\"gpt-4-turbo-restricted\\\") that provides the actual inference capability. When a user queries the composed model, the access control pipeline verifies the user has access to the composed model but never re-verifies access to the chained base model. Additionally, the model creation and import endpoints accept arbitrary base_model_id values without checking that the caller has access to that base model. Combined, this allows any user with the default model creation permission to create a model that chains to a restricted base model \u2014 and then invoke it, causing the server to dispatch the request to the restricted base model using the admin-configured API key. This vulnerability is fixed in 0.9.0.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"open-webui\",\"product\":\"open-webui\",\"versions\":[{\"version\":\"\u003c 0.9.0\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L\",\"baseScore\":7.6,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"LOW\",\"availabilityImpact\":\"LOW\"},\"exploitabilityScore\":2.8,\"impactScore\":4.7}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-05-15T20:21:00.262151Z\",\"id\":\"CVE-2026-44555\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"partial\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-862\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:openwebui:open_webui:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"0.9.0\",\"matchCriteriaId\":\"0FB90EC3-1665-446E-AA35-4AEC207A2F3B\"}]}]}],\"references\":[{\"url\":\"https://github.com/open-webui/open-webui/security/advisories/GHSA-9vvh-qmjx-p4q8\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Exploit\",\"Vendor Advisory\"]},{\"url\":\"https://github.com/open-webui/open-webui/security/advisories/GHSA-9vvh-qmjx-p4q8\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"tags\":[\"Exploit\",\"Vendor Advisory\"]}]}}",
    "redhat_vex": {
      "current_release_date": "2026-06-05T19:11:54+00:00",
      "cve": "CVE-2026-44555",
      "id": "CVE-2026-44555",
      "initial_release_date": "2026-01-01T00:00:00+00:00",
      "product_status:known_not_affected": "1",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "Open WebUI: Base Model Routing Bypasses Access Control via Model Chaining",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-44555.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-44555\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-05-15T20:21:00.262151Z\"}}}], \"references\": [{\"url\": \"https://github.com/open-webui/open-webui/security/advisories/GHSA-9vvh-qmjx-p4q8\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-05-15T20:21:17.218Z\"}}], \"cna\": {\"title\": \"Open WebUI: Base Model Routing Bypasses Access Control via Model Chaining\", \"source\": {\"advisory\": \"GHSA-9vvh-qmjx-p4q8\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 7.6, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L\", \"integrityImpact\": \"LOW\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"LOW\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"open-webui\", \"product\": \"open-webui\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.9.0\"}]}], \"references\": [{\"url\": \"https://github.com/open-webui/open-webui/security/advisories/GHSA-9vvh-qmjx-p4q8\", \"name\": \"https://github.com/open-webui/open-webui/security/advisories/GHSA-9vvh-qmjx-p4q8\", \"tags\": [\"x_refsource_CONFIRM\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.0, Open WebUI supports model composition via base_model_id: a user-defined model (e.g., \\\"Cheap Assistant\\\") can reference an existing base model (e.g., \\\"gpt-4-turbo-restricted\\\") that provides the actual inference capability. When a user queries the composed model, the access control pipeline verifies the user has access to the composed model but never re-verifies access to the chained base model. Additionally, the model creation and import endpoints accept arbitrary base_model_id values without checking that the caller has access to that base model. Combined, this allows any user with the default model creation permission to create a model that chains to a restricted base model \\u2014 and then invoke it, causing the server to dispatch the request to the restricted base model using the admin-configured API key. This vulnerability is fixed in 0.9.0.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-862\", \"description\": \"CWE-862: Missing Authorization\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-05-15T19:48:35.352Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-44555\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-05-15T20:21:22.063Z\", \"dateReserved\": \"2026-05-06T20:59:00.594Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-05-15T19:48:35.352Z\", \"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.


Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.