Browse / RAG and Vector Store Weaknesses / CVE-2026-44560
Open WebUI has Unauthorized File and Knowledge Base Content Access via RAG Vector Search
- Class
- RAG and Vector Store Weaknesses (filed by a model that read the advisory)
- Technique
- Authentication and access control
- Affected
- open-webui (PyPI)
- Gets past
- Authorisation check
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
Some retrieval paths query vector collections named by user input without the access check used elsewhere, so users can read files and knowledge bases they cannot access. (Our summary, written by a model. The source text is below.)
Details
Unauthorized File and Knowledge Base Content Access via RAG Vector Search
Affected Component
RAG source resolution in chat completion pipeline:
- backend/open_webui/retrieval/utils.py (lines 963-965, 1063-1068, 1126-1131 in get_sources_from_items)
Affected Versions
Current main branch (commit 6fdd19bf1) and likely all versions with RAG functionality.
Description
The get_sources_from_items function resolves file and knowledge base references into vector search queries during chat completion. Three of the five code paths perform vector store queries without any authorization check, allowing users to extract content from files and knowledge bases they do not have access to.
| Path | Lines | Access Check |
|------|-------|-------------|
| type: "file", full-context | 1044-1050 | ✅ has_access_to_file |
| type: "file", non-full-context (default) | 1063-1068 | ❌ None |
| type: "collection" | 1070-1118 | ✅ Present |
| type: "text" with collection_name | 963-965 | ❌ None |
| Bare collection_name/collection_names | 1126-1131 | ❌ None |
The three unprotected paths pass user-supplied collection names directly to query_collection(), which queries the vector store without any authorization. Collection names follow predictable formats: file-<file_id> for files and the knowledge base UUID for knowledge bases.
CVSS 3.1 Breakdown
| Metric | Value | Rationale |
|--------|-------|-----------|
| Attack Vector | Network (N) | Exploited remotely via chat completion API |
| Attack Complexity | Low (L) | Single API call with a known resource ID |
| Privileges Required | Low (L) | Requires a valid user account |
| User Interaction | None (N) | No victim interaction required |
| Scope | Unchanged (U) | Impact within the application's data boundary |
| Confidentiality | High (H) | Full content of private files/knowledge bases extractable |
| Integrity | None (N) | No data modification |
| Availability | None (N) | No denial of service |
Attack Scenario
- User A uploads a private document and uses it in RAG (the document is embedded into the vector store as collection
file-<file_id>). - User A shares a chat or model referencing the file with User B, or User B otherwise obtains the file ID through a legitimate interaction.
- User A later revokes User B's access to the file.
- User B sends a chat completion request referencing the revoked file: