Common Weakness Enumeration

CWE-862

Allowed-with-Review

Missing Authorization

Abstraction: Class · Status: Incomplete

API response cwe.mitre.org

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

15986 vulnerabilities reference this CWE, most recent first.

GHSA-X2F8-G477-73FR

Vulnerability from github – Published: 2025-11-21 09:30 – Updated: 2026-04-08 21:33
VLAI
Details

The Cryptocurrency (Token), Launchpad (Presale), ICO & IDO, Airdrop by TokenICO plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the 'saveDeployedContract' function in all versions up to, and including, 2.4.6. This makes it possible for authenticated attackers, with Subscriber-level access and above, to overwrite the WordPress option tokenico_deployed_contracts, poisoning the smart contract addresses displayed.

Severity
4.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2025-11773"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-11-21T08:15:50Z",
    "severity": "MODERATE"
  },
  "details": "The Cryptocurrency (Token), Launchpad (Presale), ICO \u0026 IDO, Airdrop by TokenICO plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the \u0027saveDeployedContract\u0027 function in all versions up to, and including, 2.4.6. This makes it possible for authenticated attackers, with Subscriber-level access and above, to overwrite the WordPress option `tokenico_deployed_contracts`, poisoning the smart contract addresses displayed.",
  "id": "GHSA-x2f8-g477-73fr",
  "modified": "2026-04-08T21:33:08Z",
  "published": "2025-11-21T09:30:27Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-11773"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/tokenico-cryptocurrency-token-launchpad-presale-ico-ido-airdrop/tags/2.4.6/app/RestAPI.php#L108"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/changeset?sfp_email=\u0026sfph_mail=\u0026reponame=\u0026old=3449189%40tokenico-cryptocurrency-token-launchpad-presale-ico-ido-airdrop\u0026new=3449189%40tokenico-cryptocurrency-token-launchpad-presale-ico-ido-airdrop\u0026sfp_email=\u0026sfph_mail="
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/e02597b1-eea6-4fdd-baeb-527201d1c61f?source=cve"
    }
  ],
  "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-X2FF-V5V8-M75M

Vulnerability from github – Published: 2026-07-24 17:01 – Updated: 2026-07-24 17:01
VLAI
Summary
Open WebUI: Cross-channel message overwrite via chat completion API (single-model and multimodel message_ids)
Details

Summary

Any authenticated user can overwrite the content of a message in a channel they do not belong to (including private and DM channels) by sending a chat completion request with a channel:-prefixed chat_id and a target message_id. The channel: path routes pipeline output through _make_channel_emitter, which writes to the Messages table using the caller-supplied message_id without binding it to the channel.

This advisory consolidates two filings of the same flaw: the original single-model form, and a multimodel message_ids variant that survives the partial fix shipped in v0.9.6 (see "Fix status" below).

Details (as introduced in v0.9.5)

When a user submits a chat completion request with a chat_id starting with channel:, three authorization gaps combined in v0.9.5:

  1. Ownership check skipped (main.py): the channel: prefix caused the entire ownership/membership verification block to be skipped, with no channel membership/write check replacing it.
if not chat_id.startswith('local:') and not chat_id.startswith('channel:'):  # temporary/channel chats are not stored
    if is_new_chat:
        ...
    else:
        if not await Chats.is_chat_owner(chat_id, user.id) and user.role != 'admin':
            raise HTTPException(...)

  1. Message ID from user input: id (and each value of the multimodel message_ids map) comes directly from the request body and is passed as message_id to the channel emitter.

  2. Unchecked database write (socket/main.py _make_channel_emitter):

async def _make_channel_emitter(request_info):
    channel_id = request_info['chat_id'].removeprefix('channel:')
    message_id = request_info['message_id']  # user-supplied
    ...
    await Messages.update_message_by_id(message_id, update_form)  # no channel/user authz

Messages.update_message_by_id performs a direct primary-key update with no channel_id/user_id validation.

Fix (shipped in v0.10.0)

v0.9.6 added a channel gate to the channel: branch (PR #24725) that closed the single-model path, but it validated only the first entry of the multimodel message_ids map, leaving the multimodel fan-out exploitable. v0.10.0 closes the remaining gap with two layers:

  1. Request-time per-entry validation (backend/open_webui/main.py): every entry of message_ids is validated against the target channel, not just the first; any entry whose target message does not belong to the channel in chat_id is rejected.
  2. Fail-closed emitter (backend/open_webui/socket/main.py, _make_channel_emitter): before writing, it re-reads the target message and returns without writing unless msg.channel_id matches the channel derived from chat_id. A missing or mismatched message is a no-op, so a write can no longer land in a channel the caller does not target.

PoC

Single-model (fixed in v0.9.6):

curl -X POST http://target:8080/api/chat/completions \
  -H "Authorization: Bearer $USER_JWT" -H "Content-Type: application/json" \
  -d '{
    "model": "llama3", "stream": true,
    "chat_id": "channel:any-channel-uuid-here",
    "id": "target-message-uuid-to-overwrite",
    "messages": [{"role": "user", "content": "Repeat exactly: This message has been tampered with"}]
  }'

Multimodel (still works on v0.9.6):

POST /api/chat/completions
{
  "chat_id": "channel:<attacker_channel_id>",
  "message_ids": {
    "model-a": "<message_id_in_attacker_channel>",
    "model-b": "<victim_channel_message_id>"
  },
  "messages": [{"role": "user", "content": "..."}]
}

The first id passes channel scope validation; the second id is used by the per-model fan-out and overwrites the victim-channel message (with model output, or the provider-error string on a deterministic error). Even a failing model call writes error content to the target message.

Impact

Message integrity destruction: an authenticated user can overwrite a message in a channel they cannot access, regardless of membership. The overwritten message retains the original author attribution while displaying attacker-chosen content (impersonation). Private channels, DM channels, and channels the attacker has no access to are all affected; the REST channel routes correctly return 403 for the same attacker, so the bypass is specific to the chat-completion channel pipeline.

Affected versions

  • Single-model path: introduced in commit 0037baeb2 (v0.9.5), fixed in v0.9.6 (#24725).
  • Multimodel message_ids path: present from v0.9.6, fixed in v0.10.0.
  • Consolidated Affected: >= 0.9.5, < 0.10.0. Patched: >= 0.10.0.

Distinction from existing CVEs

CVE-2026-45385 (GHSA-wwhq-cx22-f7vv) covered IDOR in the REST endpoint POST /channels/{id}/messages/{message_id}/update (routers/channels.py); its fix (commit f5e110f) only touched channels.py. This finding uses a different code path (POST /api/chat/completions with chat_id: "channel:<id>" → main.py → socket/main.py:_make_channel_emitter), untouched by that fix.

Suggested fix

Validate every value in message_ids against the channel (not just the first), rejecting any whose target message does not belong to the channel in chat_id. Additionally, make _make_channel_emitter fail closed: re-check that the target message's channel_id matches the channel before calling Messages.update_message_by_id, treating a missing or mismatched message as an error/no-op.

Consolidation

Per Open WebUI's Report Handling policy this advisory consolidates independent reports of the same chat-completions channel-overwrite flaw:

  • Single-model cross-channel overwrite via the channel: path: @sfwani (earliest filing).
  • Multimodel message_ids fan-out variant that bypasses the v0.9.6 first-id-only gate: @DavidCarliez.

One CVE for the consolidated advisory.

Severity
7.1 (High)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "open-webui"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.9.5"
            },
            {
              "fixed": "0.10.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-59714"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-07-24T17:01:07Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "## Summary\n\nAny authenticated user can overwrite the content of a message in a channel they do not belong to (including private and DM channels) by sending a chat completion request with a `channel:`-prefixed `chat_id` and a target `message_id`. The `channel:` path routes pipeline output through `_make_channel_emitter`, which writes to the `Messages` table using the caller-supplied `message_id` without binding it to the channel.\n\nThis advisory consolidates two filings of the same flaw: the original single-model form, and a multimodel `message_ids` variant that survives the partial fix shipped in v0.9.6 (see \"Fix status\" below).\n\n## Details (as introduced in v0.9.5)\n\nWhen a user submits a chat completion request with a `chat_id` starting with `channel:`, three authorization gaps combined in v0.9.5:\n\n1. **Ownership check skipped** (`main.py`): the `channel:` prefix caused the entire ownership/membership verification block to be skipped, with no channel membership/write check replacing it.\n\n```python\nif not chat_id.startswith(\u0027local:\u0027) and not chat_id.startswith(\u0027channel:\u0027):  # temporary/channel chats are not stored\n    if is_new_chat:\n        ...\n    else:\n        if not await Chats.is_chat_owner(chat_id, user.id) and user.role != \u0027admin\u0027:\n            raise HTTPException(...)\n```\n\n2. **Message ID from user input**: `id` (and each value of the multimodel `message_ids` map) comes directly from the request body and is passed as `message_id` to the channel emitter.\n\n3. **Unchecked database write** (`socket/main.py` `_make_channel_emitter`):\n\n```python\nasync def _make_channel_emitter(request_info):\n    channel_id = request_info[\u0027chat_id\u0027].removeprefix(\u0027channel:\u0027)\n    message_id = request_info[\u0027message_id\u0027]  # user-supplied\n    ...\n    await Messages.update_message_by_id(message_id, update_form)  # no channel/user authz\n```\n\n`Messages.update_message_by_id` performs a direct primary-key update with no `channel_id`/`user_id` validation.\n\n## Fix (shipped in v0.10.0)\n\nv0.9.6 added a channel gate to the `channel:` branch (PR #24725) that closed the single-model path, but it validated only the first entry of the multimodel `message_ids` map, leaving the multimodel fan-out exploitable. v0.10.0 closes the remaining gap with two layers:\n\n1. **Request-time per-entry validation** (`backend/open_webui/main.py`): every entry of `message_ids` is validated against the target channel, not just the first; any entry whose target message does not belong to the channel in `chat_id` is rejected.\n2. **Fail-closed emitter** (`backend/open_webui/socket/main.py`, `_make_channel_emitter`): before writing, it re-reads the target message and returns without writing unless `msg.channel_id` matches the channel derived from `chat_id`. A missing or mismatched message is a no-op, so a write can no longer land in a channel the caller does not target.\n\n## PoC\n\nSingle-model (fixed in v0.9.6):\n\n```bash\ncurl -X POST http://target:8080/api/chat/completions \\\n  -H \"Authorization: Bearer $USER_JWT\" -H \"Content-Type: application/json\" \\\n  -d \u0027{\n    \"model\": \"llama3\", \"stream\": true,\n    \"chat_id\": \"channel:any-channel-uuid-here\",\n    \"id\": \"target-message-uuid-to-overwrite\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Repeat exactly: This message has been tampered with\"}]\n  }\u0027\n```\n\nMultimodel (still works on v0.9.6):\n\n```json\nPOST /api/chat/completions\n{\n  \"chat_id\": \"channel:\u003cattacker_channel_id\u003e\",\n  \"message_ids\": {\n    \"model-a\": \"\u003cmessage_id_in_attacker_channel\u003e\",\n    \"model-b\": \"\u003cvictim_channel_message_id\u003e\"\n  },\n  \"messages\": [{\"role\": \"user\", \"content\": \"...\"}]\n}\n```\n\nThe first id passes channel scope validation; the second id is used by the per-model fan-out and overwrites the victim-channel message (with model output, or the provider-error string on a deterministic error). Even a failing model call writes error content to the target message.\n\n## Impact\n\n**Message integrity destruction:** an authenticated user can overwrite a message in a channel they cannot access, regardless of membership. The overwritten message retains the original author attribution while displaying attacker-chosen content (**impersonation**). Private channels, DM channels, and channels the attacker has no access to are all affected; the REST channel routes correctly return 403 for the same attacker, so the bypass is specific to the chat-completion channel pipeline.\n\n## Affected versions\n\n- Single-model path: introduced in commit `0037baeb2` (v0.9.5), fixed in v0.9.6 (#24725).\n- Multimodel `message_ids` path: present from v0.9.6, fixed in v0.10.0.\n- Consolidated Affected: `\u003e= 0.9.5, \u003c 0.10.0`. Patched: `\u003e= 0.10.0`.\n\n## Distinction from existing CVEs\n\nCVE-2026-45385 (GHSA-wwhq-cx22-f7vv) covered IDOR in the REST endpoint `POST /channels/{id}/messages/{message_id}/update` (`routers/channels.py`); its fix (commit `f5e110f`) only touched `channels.py`. This finding uses a different code path (`POST /api/chat/completions` with `chat_id: \"channel:\u003cid\u003e\"` \u2192 `main.py` \u2192 `socket/main.py:_make_channel_emitter`), untouched by that fix.\n\n## Suggested fix\n\nValidate **every** value in `message_ids` against the channel (not just the first), rejecting any whose target message does not belong to the channel in `chat_id`. Additionally, make `_make_channel_emitter` fail closed: re-check that the target message\u0027s `channel_id` matches the channel before calling `Messages.update_message_by_id`, treating a missing or mismatched message as an error/no-op.\n\n## Consolidation\n\nPer Open WebUI\u0027s Report Handling policy this advisory consolidates independent reports of the same chat-completions channel-overwrite flaw:\n\n- Single-model cross-channel overwrite via the `channel:` path: @sfwani (earliest filing).\n- Multimodel `message_ids` fan-out variant that bypasses the v0.9.6 first-id-only gate: @DavidCarliez.\n\nOne CVE for the consolidated advisory.",
  "id": "GHSA-x2ff-v5v8-m75m",
  "modified": "2026-07-24T17:01:07Z",
  "published": "2026-07-24T17:01:07Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-x2ff-v5v8-m75m"
    },
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/commit/33e4e0dcc43afcca80f9c635d762cdc76c768ba9"
    },
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/commit/ac3449cac91e62b08a7c28e54fcd044d14dea791"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/open-webui/open-webui"
    },
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/releases/tag/v0.10.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Open WebUI: Cross-channel message overwrite via chat completion API (single-model and multimodel message_ids)"
}

GHSA-X2GV-XG7R-VX8G

Vulnerability from github – Published: 2025-06-20 15:30 – Updated: 2026-04-01 18:35
VLAI
Details

Missing Authorization vulnerability in Syed Balkhi Giveaways and Contests by RafflePress allows Accessing Functionality Not Properly Constrained by ACLs. This issue affects Giveaways and Contests by RafflePress: from n/a through 1.12.17.

Severity
5.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2025-49997"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-06-20T15:15:25Z",
    "severity": "MODERATE"
  },
  "details": "Missing Authorization vulnerability in Syed Balkhi Giveaways and Contests by RafflePress allows Accessing Functionality Not Properly Constrained by ACLs. This issue affects Giveaways and Contests by RafflePress: from n/a through 1.12.17.",
  "id": "GHSA-x2gv-xg7r-vx8g",
  "modified": "2026-04-01T18:35:32Z",
  "published": "2025-06-20T15:30:40Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-49997"
    },
    {
      "type": "WEB",
      "url": "https://patchstack.com/database/wordpress/plugin/rafflepress/vulnerability/wordpress-giveaways-and-contests-by-rafflepress-plugin-1-12-17-broken-access-control-vulnerability?_s_id=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-X2H5-274P-6QQF

Vulnerability from github – Published: 2026-05-26 13:30 – Updated: 2026-05-26 13:30
VLAI
Details

The WooCommerce PayPal Payments plugin for WordPress is vulnerable to unauthorized order manipulation and information disclosure due to missing authorization checks on the ppc-create-order and ppc-get-order WC-AJAX endpoints in all versions up to, and including, 4.0.1. The ppc-create-order endpoint accepts an arbitrary WooCommerce order ID in the pay-now context without validating order ownership, allowing attackers to create PayPal orders for any WC order and write PayPal metadata to it. The ppc-get-order endpoint returns full PayPal order details for any PayPal order ID without binding to the requester's session. This makes it possible for unauthenticated attackers to chain these endpoints to manipulate other customers' order payment flows and exfiltrate sensitive order details (payer information, shipping data) by creating a PayPal order for a victim's WC order and then retrieving the PayPal order data.

Severity
8.2 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2026-9284"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-05-23T05:16:34Z",
    "severity": "HIGH"
  },
  "details": "The WooCommerce PayPal Payments plugin for WordPress is vulnerable to unauthorized order manipulation and information disclosure due to missing authorization checks on the `ppc-create-order` and `ppc-get-order` WC-AJAX endpoints in all versions up to, and including, 4.0.1. The `ppc-create-order` endpoint accepts an arbitrary WooCommerce order ID in the `pay-now` context without validating order ownership, allowing attackers to create PayPal orders for any WC order and write PayPal metadata to it. The `ppc-get-order` endpoint returns full PayPal order details for any PayPal order ID without binding to the requester\u0027s session. This makes it possible for unauthenticated attackers to chain these endpoints to manipulate other customers\u0027 order payment flows and exfiltrate sensitive order details (payer information, shipping data) by creating a PayPal order for a victim\u0027s WC order and then retrieving the PayPal order data.",
  "id": "GHSA-x2h5-274p-6qqf",
  "modified": "2026-05-26T13:30:23Z",
  "published": "2026-05-26T13:30:23Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-9284"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/woocommerce-paypal-payments/tags/3.3.2/modules/ppcp-button/src/Endpoint/CreateOrderEndpoint.php#L249"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/woocommerce-paypal-payments/tags/3.3.2/modules/ppcp-button/src/Endpoint/GetOrderEndpoint.php#L44"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/woocommerce-paypal-payments/trunk/modules/ppcp-button/src/Endpoint/CreateOrderEndpoint.php#L249"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/woocommerce-paypal-payments/trunk/modules/ppcp-button/src/Endpoint/GetOrderEndpoint.php#L44"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/changeset?sfp_email=\u0026sfph_mail=\u0026reponame=\u0026old=3497597%40woocommerce-paypal-payments\u0026new=3497597%40woocommerce-paypal-payments\u0026sfp_email=\u0026sfph_mail="
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/d5fa3282-b3be-4ea1-9865-011dea828a25?source=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-X2H8-Q8W2-33XM

Vulnerability from github – Published: 2026-01-17 06:30 – Updated: 2026-01-17 06:30
VLAI
Details

The Community Events plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the ajax_admin_event_approval() function in all versions up to, and including, 1.5.6. This makes it possible for unauthenticated attackers to approve arbitrary events via the 'eventlist' parameter.

Severity
5.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2025-14029"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-01-17T05:16:10Z",
    "severity": "MODERATE"
  },
  "details": "The Community Events plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the ajax_admin_event_approval() function in all versions up to, and including, 1.5.6. This makes it possible for unauthenticated attackers to approve arbitrary events via the \u0027eventlist\u0027 parameter.",
  "id": "GHSA-x2h8-q8w2-33xm",
  "modified": "2026-01-17T06:30:36Z",
  "published": "2026-01-17T06:30:36Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-14029"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/community-events/tags/1.5.5/community-events.php#L160"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/community-events/tags/1.5.5/community-events.php#L64"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/community-events/trunk/community-events.php#L160"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/changeset?sfp_email=\u0026sfph_mail=\u0026reponame=\u0026old=3437116%40community-events\u0026new=3437116%40community-events\u0026sfp_email=\u0026sfph_mail="
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/098c3f4c-b6bc-462a-98ef-30e6a68d74cf?source=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-X2HV-7JF3-P2RF

Vulnerability from github – Published: 2025-01-07 06:32 – Updated: 2025-01-07 06:32
VLAI
Details

The Popup – MailChimp, GetResponse and ActiveCampaign Intergrations plugin for WordPress is vulnerable to unauthorized loss of data due to a missing capability check on the 'upc_delete_db_data' AJAX action in all versions up to, and including, 3.2.6. This makes it possible for unauthenticated attackers to delete the DB data for the plugin.

Severity
5.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2024-12158"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-01-07T05:15:15Z",
    "severity": "MODERATE"
  },
  "details": "The Popup \u2013 MailChimp, GetResponse and ActiveCampaign Intergrations plugin for WordPress is vulnerable to unauthorized loss of data due to a missing capability check on the \u0027upc_delete_db_data\u0027 AJAX action in all versions up to, and including, 3.2.6. This makes it possible for unauthenticated attackers to delete the DB data for the plugin.",
  "id": "GHSA-x2hv-7jf3-p2rf",
  "modified": "2025-01-07T06:32:15Z",
  "published": "2025-01-07T06:32:15Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-12158"
    },
    {
      "type": "WEB",
      "url": "https://wordpress.org/plugins/ultimate-popup-creator"
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/93a698df-fd68-4fbc-946e-a9b5a7f93b71?source=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-X2JJ-VRXQ-66GV

Vulnerability from github – Published: 2025-03-31 15:30 – Updated: 2026-04-01 18:34
VLAI
Details

Missing Authorization vulnerability in acmemediakits ACME Divi Modules allows Exploiting Incorrectly Configured Access Control Security Levels. This issue affects ACME Divi Modules: from n/a through 1.3.5.

Severity
4.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2025-31540"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-03-31T13:15:48Z",
    "severity": "MODERATE"
  },
  "details": "Missing Authorization vulnerability in acmemediakits ACME Divi Modules allows Exploiting Incorrectly Configured Access Control Security Levels. This issue affects ACME Divi Modules: from n/a through 1.3.5.",
  "id": "GHSA-x2jj-vrxq-66gv",
  "modified": "2026-04-01T18:34:15Z",
  "published": "2025-03-31T15:30:44Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-31540"
    },
    {
      "type": "WEB",
      "url": "https://patchstack.com/database/wordpress/plugin/acme-divi-modules/vulnerability/wordpress-acme-divi-modules-plugin-1-3-5-broken-access-control-vulnerability?_s_id=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-X2M8-53H4-6HCH

Vulnerability from github – Published: 2026-04-03 03:27 – Updated: 2026-04-28 18:16
VLAI
Summary
OpenClaw: Discord voice ingress authorization can be bypassed via channel, name, and stale-role validation gaps
Details

Summary

Discord voice ingress authorization can be bypassed via channel, name, and stale-role validation gaps

Current Maintainer Triage

  • Status: narrow
  • Assessment: Real in shipped v2026.3.28 Discord voice ingress, but impact is channel/member allowlist bypass rather than a broader critical auth break and mainline fix is unreleased.

Affected Packages / Versions

  • Package: openclaw (npm)
  • Latest published npm version: 2026.3.31
  • Vulnerable version range: <=2026.3.28
  • Patched versions: >= 2026.3.31
  • First stable tag containing the fix: v2026.3.31

Fix Commit(s)

  • dba96e7507e0900f120e5e28e57755d69bf78759 — 2026-03-31T21:29:13+09:00

OpenClaw thanks @cyjhhh for reporting.

Severity
2.3 (Low)
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:L/SA:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 2026.3.28"
      },
      "package": {
        "ecosystem": "npm",
        "name": "openclaw"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "2026.3.31"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-41382"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-03T03:27:38Z",
    "nvd_published_at": null,
    "severity": "LOW"
  },
  "details": "## Summary\nDiscord voice ingress authorization can be bypassed via channel, name, and stale-role validation gaps\n\n## Current Maintainer Triage\n- Status: narrow\n- Assessment: Real in shipped v2026.3.28 Discord voice ingress, but impact is channel/member allowlist bypass rather than a broader critical auth break and mainline fix is unreleased.\n\n## Affected Packages / Versions\n- Package: `openclaw` (npm)\n- Latest published npm version: `2026.3.31`\n- Vulnerable version range: `\u003c=2026.3.28`\n- Patched versions: `\u003e= 2026.3.31`\n- First stable tag containing the fix: `v2026.3.31`\n\n## Fix Commit(s)\n- `dba96e7507e0900f120e5e28e57755d69bf78759` \u2014 2026-03-31T21:29:13+09:00\n\nOpenClaw thanks @cyjhhh for reporting.",
  "id": "GHSA-x2m8-53h4-6hch",
  "modified": "2026-04-28T18:16:57Z",
  "published": "2026-04-03T03:27:38Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/openclaw/openclaw/security/advisories/GHSA-x2m8-53h4-6hch"
    },
    {
      "type": "WEB",
      "url": "https://github.com/openclaw/openclaw/commit/dba96e7507e0900f120e5e28e57755d69bf78759"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/openclaw/openclaw"
    },
    {
      "type": "WEB",
      "url": "https://github.com/openclaw/openclaw/releases/tag/v2026.3.31"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:L/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "OpenClaw: Discord voice ingress authorization can be bypassed via channel, name, and stale-role validation gaps"
}

GHSA-X2P4-4CW9-M5CH

Vulnerability from github – Published: 2026-03-26 06:30 – Updated: 2026-03-26 06:30
VLAI
Details

The Blog2Social: Social Media Auto Post & Scheduler plugin for WordPress is vulnerable to unauthorized data loss in all versions up to, and including, 8.8.2. This is due to the resetSocialMetaTags() function only verifying that the user has the 'read' capability and a valid b2s_security_nonce, both of which are available to Subscriber-level users, as the plugin grants 'blog2social_access' capability to all roles upon activation, allowing them to access the plugin's admin pages where the nonce is output. This makes it possible for authenticated attackers, with Subscriber-level access and above, to delete all _b2s_post_meta records from the wp_postmeta table, permanently removing all custom social media meta tags for every post on the site.

Severity
4.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2026-4331"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-03-26T05:16:40Z",
    "severity": "MODERATE"
  },
  "details": "The Blog2Social: Social Media Auto Post \u0026 Scheduler plugin for WordPress is vulnerable to unauthorized data loss in all versions up to, and including, 8.8.2. This is due to the resetSocialMetaTags() function only verifying that the user has the \u0027read\u0027 capability and a valid b2s_security_nonce, both of which are available to Subscriber-level users, as the plugin grants \u0027blog2social_access\u0027 capability to all roles upon activation, allowing them to access the plugin\u0027s admin pages where the nonce is output. This makes it possible for authenticated attackers, with Subscriber-level access and above, to delete all _b2s_post_meta records from the wp_postmeta table, permanently removing all custom social media meta tags for every post on the site.",
  "id": "GHSA-x2p4-4cw9-m5ch",
  "modified": "2026-03-26T06:30:21Z",
  "published": "2026-03-26T06:30:21Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-4331"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/blog2social/tags/8.8.2/includes/Ajax/Post.php#L1281"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/blog2social/tags/8.8.2/includes/Ajax/Post.php#L1290"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/blog2social/tags/8.8.2/includes/Ajax/Post.php#L37"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/blog2social/tags/8.8.2/includes/Loader.php#L2202"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/blog2social/tags/8.8.3/includes/Ajax/Post.php#L1301"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/blog2social/trunk/includes/Ajax/Post.php#L1281"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/blog2social/trunk/includes/Ajax/Post.php#L1290"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/blog2social/trunk/includes/Ajax/Post.php#L37"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/blog2social/trunk/includes/Loader.php#L2202"
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/7dc46bc4-ecfb-438f-b951-7b957489cd96?source=cve"
    }
  ],
  "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-X2PJ-X7HV-QM35

Vulnerability from github – Published: 2026-04-24 09:30 – Updated: 2026-04-24 09:30
VLAI
Details

The Liaison Site Prober plugin for WordPress is vulnerable to Information Exposure in all versions up to and including 1.2.1 via the /wp-json/site-prober/v1/logs REST API endpoint. The permissions_read() permission callback unconditionally returns true (via __return_true()) instead of checking for appropriate capabilities. This makes it possible for unauthenticated attackers to retrieve sensitive audit log data including IP addresses, user IDs, usernames, login/logout events, failed login attempts, and detailed activity descriptions.

Severity
5.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2026-3569"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-04-24T08:16:30Z",
    "severity": "MODERATE"
  },
  "details": "The Liaison Site Prober plugin for WordPress is vulnerable to Information Exposure in all versions up to and including 1.2.1 via the /wp-json/site-prober/v1/logs REST API endpoint. The permissions_read() permission callback unconditionally returns true (via __return_true()) instead of checking for appropriate capabilities. This makes it possible for unauthenticated attackers to retrieve sensitive audit log data including IP addresses, user IDs, usernames, login/logout events, failed login attempts, and detailed activity descriptions.",
  "id": "GHSA-x2pj-x7hv-qm35",
  "modified": "2026-04-24T09:30:30Z",
  "published": "2026-04-24T09:30:30Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-3569"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/liaison-site-prober/tags/1.2.1/includes/class-liaison-rest-controller.php#L19"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/liaison-site-prober/tags/1.2.1/includes/class-liaison-rest-controller.php#L50"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/liaison-site-prober/tags/1.2.1/includes/class-liaison-rest-controller.php#L90"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/liaison-site-prober/trunk/includes/class-liaison-rest-controller.php#L19"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/liaison-site-prober/trunk/includes/class-liaison-rest-controller.php#L50"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/browser/liaison-site-prober/trunk/includes/class-liaison-rest-controller.php#L90"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/changeset?sfp_email=\u0026sfph_mail=\u0026reponame=\u0026old=3481019%40liaison-site-prober\u0026new=3481019%40liaison-site-prober\u0026sfp_email=\u0026sfph_mail="
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/eda5addb-40e2-4187-b803-34500b36be0a?source=cve"
    }
  ],
  "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"
    }
  ]
}
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) [REF-229] 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 access control checks are performed related to the business logic. These checks may be different than the access control checks that are applied 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 [REF-7].

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-665: Exploitation of Thunderbolt Protection Flaws

An adversary leverages a firmware weakness within the Thunderbolt protocol, on a computing device to manipulate Thunderbolt controller firmware in order to exploit vulnerabilities in the implementation of authorization and verification schemes within Thunderbolt protection mechanisms. Upon gaining physical access to a target device, the adversary conducts high-level firmware manipulation of the victim Thunderbolt controller SPI (Serial Peripheral Interface) flash, through the use of a SPI Programing device and an external Thunderbolt device, typically as the target device is booting up. If successful, this allows the adversary to modify memory, subvert authentication mechanisms, spoof identities and content, and extract data and memory from the target device. Currently 7 major vulnerabilities exist within Thunderbolt protocol with 9 attack vectors as noted in the Execution Flow.

← Back to the CWE list