GHSA-X2FF-V5V8-M75M
Vulnerability from github – Published: 2026-07-24 17:01 – Updated: 2026-07-24 17:01Summary
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:
- Ownership check skipped (
main.py): thechannel: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(...)
-
Message ID from user input:
id(and each value of the multimodelmessage_idsmap) comes directly from the request body and is passed asmessage_idto the channel emitter. -
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:
- Request-time per-entry validation (
backend/open_webui/main.py): every entry ofmessage_idsis validated against the target channel, not just the first; any entry whose target message does not belong to the channel inchat_idis rejected. - Fail-closed emitter (
backend/open_webui/socket/main.py,_make_channel_emitter): before writing, it re-reads the target message and returns without writing unlessmsg.channel_idmatches the channel derived fromchat_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_idspath: 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_idsfan-out variant that bypasses the v0.9.6 first-id-only gate: @DavidCarliez.
One CVE for the consolidated advisory.
{
"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)"
}
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.