Vulnerability-Lookup

CVE-2026-45387 (GCVE-0-2026-45387)

Vulnerability from cvelistv5 – Published: 2026-05-15 20:32 – Updated: 2026-05-15 21:08

Title

Open WebUI: Sharing models for others to use (read permission) also exposes model details (system prompt leakage)

Summary

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.5, when setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model's system prompt. However users may consider their system prompt confidential, so this is considered a security issue. This vulnerability is fixed in 0.9.5.

Severity

4.3 (Medium)


                        
                          CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N

SSVC

Exploitation: poc Automatable: no Technical Impact: partial

CISA Coordinator (v2.0.3)

CWE

CWE-200 - Exposure of Sensitive Information to an Unauthorized Actor

Assigner

GitHub_M

References

1 reference

URL	Tags
https://github.com/open-webui/open-webui/security…	x_refsource_CONFIRM

Impacted products

1 product

Vendor	Product	Version
open-webui	open-webui	Affected: < 0.9.5

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-45387",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-15T21:08:24.440775Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-15T21:08:29.508Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "open-webui",
          "vendor": "open-webui",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.9.5"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.5, when setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model\u0027s system prompt. However users may consider their system prompt confidential, so this is considered a security issue. This vulnerability is fixed in 0.9.5."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 4.3,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "LOW",
            "integrityImpact": "NONE",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-200",
              "description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-15T20:32:02.012Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr"
        }
      ],
      "source": {
        "advisory": "GHSA-h2cw-7qw9-56xr",
        "discovery": "UNKNOWN"
      },
      "title": "Open WebUI: Sharing models for others to use (read permission) also exposes model details (system prompt leakage)"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-45387",
    "datePublished": "2026-05-15T20:32:02.012Z",
    "dateReserved": "2026-05-12T00:51:29.087Z",
    "dateUpdated": "2026-05-15T21:08:29.508Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-45387",
      "date": "2026-06-03",
      "epss": "0.00026",
      "percentile": "0.07878"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-45387\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-05-15T21:16:37.177\",\"lastModified\":\"2026-05-19T03:05:44.803\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.5, when setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model\u0027s system prompt. However users may consider their system prompt confidential, so this is considered a security issue. This vulnerability is fixed in 0.9.5.\"}],\"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:L/I:N/A:N\",\"baseScore\":4.3,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"LOW\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.8,\"impactScore\":1.4}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-200\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:openwebui:open_webui:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"0.9.5\",\"matchCriteriaId\":\"19F64B41-71DA-4E31-A040-1C351A537567\"}]}]}],\"references\":[{\"url\":\"https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Exploit\",\"Vendor Advisory\"]},{\"url\":\"https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"tags\":[\"Exploit\",\"Vendor Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-45387\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-05-15T21:08:24.440775Z\"}}}], \"references\": [{\"url\": \"https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-05-15T21:08:18.979Z\"}}], \"cna\": {\"title\": \"Open WebUI: Sharing models for others to use (read permission) also exposes model details (system prompt leakage)\", \"source\": {\"advisory\": \"GHSA-h2cw-7qw9-56xr\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 4.3, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"LOW\"}}], \"affected\": [{\"vendor\": \"open-webui\", \"product\": \"open-webui\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.9.5\"}]}], \"references\": [{\"url\": \"https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr\", \"name\": \"https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr\", \"tags\": [\"x_refsource_CONFIRM\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.5, when setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model\u0027s system prompt. However users may consider their system prompt confidential, so this is considered a security issue. This vulnerability is fixed in 0.9.5.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-200\", \"description\": \"CWE-200: Exposure of Sensitive Information to an Unauthorized Actor\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-05-15T20:32:02.012Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-45387\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-05-15T21:08:29.508Z\", \"dateReserved\": \"2026-05-12T00:51:29.087Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-05-15T20:32:02.012Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-45387

Vulnerability from fkie_nvd - Published: 2026-05-15 21:16 - Updated: 2026-05-19 03:05

Severity

4.3 (Medium) - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr	Exploit, Vendor Advisory
	134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr	Exploit, Vendor Advisory

Impacted products

	Vendor	Product	Version
	openwebui	open_webui	*

JSON

To clipboard

{
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:openwebui:open_webui:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "19F64B41-71DA-4E31-A040-1C351A537567",
              "versionEndExcluding": "0.9.5",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.5, when setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model\u0027s system prompt. However users may consider their system prompt confidential, so this is considered a security issue. This vulnerability is fixed in 0.9.5."
    }
  ],
  "id": "CVE-2026-45387",
  "lastModified": "2026-05-19T03:05:44.803",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "NONE",
          "baseScore": 4.3,
          "baseSeverity": "MEDIUM",
          "confidentialityImpact": "LOW",
          "integrityImpact": "NONE",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 1.4,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-05-15T21:16:37.177",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Exploit",
        "Vendor Advisory"
      ],
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "tags": [
        "Exploit",
        "Vendor Advisory"
      ],
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-200"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-H2CW-7QW9-56XR

Vulnerability from github – Published: 2026-05-14 20:26 – Updated: 2026-05-15 23:54

Summary

Open WebUI: Sharing models for others to use (read permission) also exposes model details (system prompt leakage)

Details

Summary

When setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model's system prompt.

However users may consider their system prompt confidential, so we consider this a security issue.

Compare https://genai.owasp.org/llmrisk/llm072025-system-prompt-leakage/ or prompt injections to get popular chatbots on the internet to reveal their prompt.

Details

We discovered that users can open the workspace model edit page /workspace/models/edit?id=notmymodel for models that do not appear in their workspace.

Saving is not possible, that permission check is correct.

On the API level:

/api/v1/models/model?id=notmymodel -> returns the model details, most importantly params.system
even though /api/v1/models/list does NOT contain the model since it checks for write permission.
/api/models contains the model correctly and does not reveal the system prompt.

It seems inconsistent that the REST API list does not contain an item, but if you know the id, you can access it anyway.

PoC

create model
give read permission to group with another user
other user can access /api/v1/models/model?id=notmymodel

Impact

System prommpt leakage

If this is intended behavior for the "read" permission, maybe there should be an additional "use" permission (which would be 99% of use cases of the read permission i believe).

Severity

4.3 (Medium)


                  
                    CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 0.9.4"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "open-webui"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.9.5"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-45387"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-200"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-14T20:26:03Z",
    "nvd_published_at": "2026-05-15T21:16:37Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\nWhen setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model\u0027s system prompt.\n\nHowever users may consider their system prompt confidential, so we consider this a security issue.\n\nCompare https://genai.owasp.org/llmrisk/llm072025-system-prompt-leakage/ or prompt injections to get popular chatbots on the internet to reveal their prompt.\n\n### Details\n\nWe discovered that users can open the workspace model edit page /workspace/models/edit?id=notmymodel for models that do not appear in their workspace.\n\nSaving is not possible, that permission check is correct.\n\nOn the API level:\n\n- ```/api/v1/models/model?id=notmymodel``` -\u003e returns the model details, most importantly params.system\n- even though ```/api/v1/models/list``` does NOT contain the model since it checks for write permission.\n- ```/api/models``` contains the model correctly and does not reveal the system prompt.\n\nIt seems inconsistent that the REST API list does not contain an item, but if you know the id, you can access it anyway.\n\n### PoC\n- create model\n- give read permission to group with another user\n- other user can access ```/api/v1/models/model?id=notmymodel```\n\n### Impact\nSystem prommpt leakage\n\nIf this is intended behavior for the \"read\" permission, maybe there should be an additional \"use\" permission (which would be 99% of use cases of the read permission i believe).",
  "id": "GHSA-h2cw-7qw9-56xr",
  "modified": "2026-05-15T23:54:25Z",
  "published": "2026-05-14T20:26:03Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-45387"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/open-webui/open-webui"
    },
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/releases/tag/v0.9.5"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Open WebUI: Sharing models for others to use (read permission) also exposes model details (system prompt leakage)"
}

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.

Action not permitted

CVE-2026-45387 (GCVE-0-2026-45387)

FKIE_CVE-2026-45387

GHSA-H2CW-7QW9-56XR

Summary

Details

PoC

Impact

Tags

Sightings

Nomenclature