Vulnerability-Lookup

CVE-2026-45350 (GCVE-0-2026-45350)

Vulnerability from cvelistv5 – Published: 2026-05-15 21:23 – Updated: 2026-05-15 22:21

Title

Open WebUI: Chat completion API allows tool restrictions to be bypassed

Summary

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.6, there is a vulnerability in chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access. In the chat_completion API, the parameters tool_ids and tool_servers are supplied by the user. These parameters are used to create a tools_dict by the middleware. This is then used by get_tool_by_id to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. This vulnerability is fixed in 0.8.6.

Severity ?

7.1 (High)


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

CWE

CWE-862 - Missing Authorization

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: < 0.8.6

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-45350",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-15T22:18:20.873238Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-15T22:21:32.823Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "open-webui",
          "vendor": "open-webui",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.8.6"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.6, there is a vulnerability in chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access. In the chat_completion API, the parameters tool_ids and tool_servers are supplied by the user. These parameters are used to create a tools_dict by the middleware. This is then used by get_tool_by_id to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. This vulnerability is fixed in 0.8.6."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 7.1,
            "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:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-862",
              "description": "CWE-862: Missing Authorization",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-15T21:23:49.724Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w"
        }
      ],
      "source": {
        "advisory": "GHSA-4pcg-253r-rf9w",
        "discovery": "UNKNOWN"
      },
      "title": "Open WebUI: Chat completion API allows tool restrictions to be bypassed"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-45350",
    "datePublished": "2026-05-15T21:23:49.724Z",
    "dateReserved": "2026-05-11T21:40:08.178Z",
    "dateUpdated": "2026-05-15T22:21:32.823Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-45350",
      "date": "2026-05-24",
      "epss": "0.00056",
      "percentile": "0.17552"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-45350\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-05-15T22:16:55.323\",\"lastModified\":\"2026-05-18T19:27:38.780\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.6, there is a vulnerability in chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access. In the chat_completion API, the parameters tool_ids and tool_servers are supplied by the user. These parameters are used to create a tools_dict by the middleware. This is then used by get_tool_by_id to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. This vulnerability is fixed in 0.8.6.\"}],\"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:N\",\"baseScore\":7.1,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"LOW\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.8,\"impactScore\":4.2}]},\"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\":\"0.8.6\",\"matchCriteriaId\":\"98042D01-E16B-45CE-9BBC-E5A6E2AA2370\"}]}]}],\"references\":[{\"url\":\"https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Exploit\",\"Patch\",\"Vendor Advisory\"]},{\"url\":\"https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"tags\":[\"Exploit\",\"Patch\",\"Vendor Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-45350\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-05-15T22:18:20.873238Z\"}}}], \"references\": [{\"url\": \"https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-05-15T22:18:32.106Z\"}}], \"cna\": {\"title\": \"Open WebUI: Chat completion API allows tool restrictions to be bypassed\", \"source\": {\"advisory\": \"GHSA-4pcg-253r-rf9w\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 7.1, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N\", \"integrityImpact\": \"LOW\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"open-webui\", \"product\": \"open-webui\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.8.6\"}]}], \"references\": [{\"url\": \"https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w\", \"name\": \"https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w\", \"tags\": [\"x_refsource_CONFIRM\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.6, there is a vulnerability in chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access. In the chat_completion API, the parameters tool_ids and tool_servers are supplied by the user. These parameters are used to create a tools_dict by the middleware. This is then used by get_tool_by_id to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. This vulnerability is fixed in 0.8.6.\"}], \"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\": \"2026-05-15T21:23:49.724Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-45350\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-05-15T22:21:32.823Z\", \"dateReserved\": \"2026-05-11T21:40:08.178Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-05-15T21:23:49.724Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-45350

Vulnerability from fkie_nvd - Published: 2026-05-15 22:16 - Updated: 2026-05-18 19:27

Severity ?

7.1 (High) - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w	Exploit, Patch, Vendor Advisory
	134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w	Exploit, Patch, 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": "98042D01-E16B-45CE-9BBC-E5A6E2AA2370",
              "versionEndExcluding": "0.8.6",
              "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 0.8.6, there is a vulnerability in chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access. In the chat_completion API, the parameters tool_ids and tool_servers are supplied by the user. These parameters are used to create a tools_dict by the middleware. This is then used by get_tool_by_id to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. This vulnerability is fixed in 0.8.6."
    }
  ],
  "id": "CVE-2026-45350",
  "lastModified": "2026-05-18T19:27:38.780",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "NONE",
          "baseScore": 7.1,
          "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:N",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 4.2,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-05-15T22:16:55.323",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Exploit",
        "Patch",
        "Vendor Advisory"
      ],
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "tags": [
        "Exploit",
        "Patch",
        "Vendor Advisory"
      ],
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-862"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-4PCG-253R-RF9W

Vulnerability from github – Published: 2026-05-14 20:24 – Updated: 2026-05-19 15:59

Summary

Open WebUI's chat completion API allows tool restrictions to be bypassed

Details

Summary

Open WebUI v0.6.43 contains a vulnerability in its chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access.

Details

In the chat_completion API, the parameters tool_ids and tool_servers are supplied by the user. These parameters are used to create a tools_dict by the middleware. This is then used by get_tool_by_id to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege.

PoC

To reproduce the issue, create an admin user and create an external tool via the admin settings. Set the type to "MCP Streamable HTTP" for the tool, and the url pointing to a mcp server. For example, the public instance of the "Fetch" mcp server can be used, which is located at "https://remote.mcpservers.org/fetch/mcp". Other mcp servers, e.g. the GitHub MCP server can also be used. Then set the "Auth" field appropriately. (Fetch mcp does not require Auth to be set).

Set the ID, name and description for the MCP server and set visibility to private. This should prevent any user from using the mcp server. (For the example below, we use the fetch mcp server and set the ID to 1)

Next create a user with low privilege and enable API keys from the admin settings.

Then use the chat completion API with the low privilege user with a prompt specifying the use of the restricted tool, and include the id of the tool in the tool_ids parameter. For example, to use the fetch mcp server set up before:

def chat_with_model(token):
    url = 'http://localhost:3000/api/chat/completions'
    headers = {
        'Authorization': f'Bearer {token}',
        'Content-Type': 'application/json'
    }
    data = {
      "model": "llama3.1:latest",
      "messages": [
        {
          "role": "user",
          "content": "Use the fetch tool to fetch content of the url https://raw.githubusercontent.com/modelcontextprotocol/servers/refs/heads/main/src/fetch/LICENSE"
        }],

        "tool_ids" : [
            "server:mcp:1",
        ],
    }
    response = requests.post(url, headers=headers, json=data)
    return response.json()

Note that the tool will be used to fetch the content of the file, despite the tool is restricted and has it's visibility set to private

Impact

This issue may lead to restricted tools being invoked by users via the chat completion API

Resolution

Fixed across two releases

Local Tool records (tool_ids: ["<tool_id>"] referencing a stored Tool): fixed in commit 9b06fdc8f, first released in v0.7.0. get_tools() in backend/open_webui/utils/tools.py (line 166) now resolves the caller's group memberships and rejects each requested tool_id whose owner isn't the caller and for which no AccessGrants.has_access(resource_type='tool', permission='read') grant exists. Admins continue to bypass when BYPASS_ADMIN_ACCESS_CONTROL is enabled (its documented UI/posture purpose).
Admin-configured MCP servers (tool_ids: ["server:mcp:<id>"], the report's exact PoC): fixed in commit 4737e1f11, first released in v0.8.6. The MCP-resolution loop in backend/open_webui/utils/middleware.py (line 2670) now calls has_connection_access(user, mcp_server_connection) and skips the server with a warning if the user has no grant — the server's stored credentials are never used on behalf of an unauthorized caller.

Users on >= 0.8.6 are not affected.

Severity ?

7.1 (High)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 0.8.5"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "open-webui"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.8.6"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-45350"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-14T20:24:48Z",
    "nvd_published_at": "2026-05-15T22:16:55Z",
    "severity": "HIGH"
  },
  "details": "### Summary\nOpen WebUI v0.6.43 contains a vulnerability in its chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access.\n\n\n### Details\nIn the [chat_completion](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1529) API, the parameters [tool_ids and tool_servers](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1613-L1614) are supplied by the user. These parameters are used to [create a tools_dict by the middleware](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/utils/middleware.py#L1394). This is then used by [get_tool_by_id](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/models/tools.py#L139) to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege.\n### PoC\nTo reproduce the issue, create an admin user and create an external tool via the admin settings. Set the type to \"MCP Streamable HTTP\" for the tool, and the url pointing to a mcp server. For example, the public instance of the [\"Fetch\" mcp server](https://github.com/modelcontextprotocol/servers/blob/main/src/fetch/README.md) can be used, which is located at \"https://remote.mcpservers.org/fetch/mcp\". Other mcp servers, e.g. the GitHub MCP server can also be used. Then set the \"Auth\" field appropriately. (Fetch mcp does not require Auth to be set).\n\nSet the ID, name and description for the MCP server and set visibility to private. This should prevent any user from using the mcp server. (For the example below, we use the fetch mcp server and set the ID to 1)\n\nNext create a user with low privilege and enable API keys from the admin settings.\n\nThen use the chat completion API with the low privilege user with a prompt specifying the use of the restricted tool, and include the id of the tool in the tool_ids parameter. For example, to use the fetch mcp server set up before:\n\n```\ndef chat_with_model(token):\n    url = \u0027http://localhost:3000/api/chat/completions\u0027\n    headers = {\n        \u0027Authorization\u0027: f\u0027Bearer {token}\u0027,\n        \u0027Content-Type\u0027: \u0027application/json\u0027\n    }\n    data = {\n      \"model\": \"llama3.1:latest\",\n      \"messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"Use the fetch tool to fetch content of the url https://raw.githubusercontent.com/modelcontextprotocol/servers/refs/heads/main/src/fetch/LICENSE\"\n        }],\n        \n        \"tool_ids\" : [\n            \"server:mcp:1\",\n        ],\n    }\n    response = requests.post(url, headers=headers, json=data)\n    return response.json()\n```\n\nNote that the tool will be used to fetch the content of the file, despite the tool is restricted and has it\u0027s visibility set to private\n\n### Impact\nThis issue may lead to restricted tools being invoked by users via the chat completion API\n\n## Resolution\n\nFixed across two releases\n\n- **Local Tool records** (`tool_ids: [\"\u003ctool_id\u003e\"]` referencing a stored Tool): fixed in commit [9b06fdc8f](https://github.com/open-webui/open-webui/commit/9b06fdc8fe1c933071610336be05f11e77e6c8eb), first released in **v0.7.0**. `get_tools()` in `backend/open_webui/utils/tools.py` (line 166) now resolves the caller\u0027s group memberships and rejects each requested `tool_id` whose owner isn\u0027t the caller and for which no `AccessGrants.has_access(resource_type=\u0027tool\u0027, permission=\u0027read\u0027)` grant exists. Admins continue to bypass when `BYPASS_ADMIN_ACCESS_CONTROL` is enabled (its documented UI/posture purpose).\n\n- **Admin-configured MCP servers** (`tool_ids: [\"server:mcp:\u003cid\u003e\"]`, the report\u0027s exact PoC): fixed in commit [4737e1f11](https://github.com/open-webui/open-webui/commit/4737e1f11), first released in **v0.8.6**. The MCP-resolution loop in `backend/open_webui/utils/middleware.py` (line 2670) now calls `has_connection_access(user, mcp_server_connection)` and skips the server with a warning if the user has no grant \u2014 the server\u0027s stored credentials are never used on behalf of an unauthorized caller.\n\nUsers on `\u003e= 0.8.6` are not affected.",
  "id": "GHSA-4pcg-253r-rf9w",
  "modified": "2026-05-19T15:59:53Z",
  "published": "2026-05-14T20:24:48Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-4pcg-253r-rf9w"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-45350"
    },
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/commit/4737e1f11"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/open-webui/open-webui"
    },
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/releases/tag/v0.8.6"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Open WebUI\u0027s chat completion API allows tool restrictions to be bypassed"
}

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-2026-45350 (GCVE-0-2026-45350)

FKIE_CVE-2026-45350

GHSA-4PCG-253R-RF9W

Summary

Details

PoC

Impact

Resolution

Tags

Sightings

Nomenclature