CVE-2026-45397: Open webui Open WebUI Vulnerable To Unauthenticated Vulnerability

{
  "schema_version" : "1.4.0",
  "id" : "GHSA-65pg-qhhw-mxwg",
  "modified" : "2026-05-15T23:55:19Z",
  "published" : "2026-05-14T20:26:34Z",
  "aliases" : [ "CVE-2026-45397" ],
  "summary" : "Open WebUI Vulnerable to Unauthenticated RAG Configuration Disclosure",
  "details" : "**Vulnerability Type:** Information Disclosure / Missing Authentication  \n**Severity:** Medium  \n**Component:** `backend/open_webui/routers/retrieval.py` — `get_status()` (`GET /`)  \n**Affected Endpoint:** `GET /api/v1/retrieval/`  \n**Affected Version:** Open WebUI `main` branch — confirmed unpatched through **v0.9.2**  \n**Authentication Required:** None — internet-facing with zero credentials  \n**CVSSv3.1 Score:** 5.3 (AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N)\n\n---\n\n## Summary\n\n`GET /api/v1/retrieval/` returns live RAG pipeline configuration to any unauthenticated HTTP client. No `Authorization` header, cookie, or API key is required. Every adjacent endpoint on the same router (`/embedding`, `/config`) is correctly guarded by `get_admin_user` making this a targeted omission.\n\n---\n\n## Root Cause\n\n`backend/open_webui/routers/retrieval.py:262`\n\n```python\n@router.get('/')\nasync def get_status(request: Request):   # ← no Depends(get_verified_user)\n    return {\n        'status': True,\n        'CHUNK_SIZE': request.app.state.config.CHUNK_SIZE,\n        'CHUNK_OVERLAP': request.app.state.config.CHUNK_OVERLAP,\n        'RAG_TEMPLATE': request.app.state.config.RAG_TEMPLATE,\n        'RAG_EMBEDDING_ENGINE': request.app.state.config.RAG_EMBEDDING_ENGINE,\n        'RAG_EMBEDDING_MODEL': request.app.state.config.RAG_EMBEDDING_MODEL,\n        'RAG_RERANKING_MODEL': request.app.state.config.RAG_RERANKING_MODEL,\n        'RAG_EMBEDDING_BATCH_SIZE': request.app.state.config.RAG_EMBEDDING_BATCH_SIZE,\n        'ENABLE_ASYNC_EMBEDDING': request.app.state.config.ENABLE_ASYNC_EMBEDDING,\n        'RAG_EMBEDDING_CONCURRENT_REQUESTS': request.app.state.config.RAG_EMBEDDING_CONCURRENT_REQUESTS,\n    }\n```\n\nCompare with every adjacent endpoint on the same router:\n\n```python\n@router.get('/embedding')\nasync def get_embedding_config(request: Request, user=Depends(get_admin_user)):  # ✅\n\n@router.get('/config')\nasync def get_rag_config(request: Request, user=Depends(get_admin_user)):        # ✅\n```\n\n---\n\n## Proof Of Concept — No Token Required\n\n```bash\ncurl -s http://TARGET/api/v1/retrieval/\n```\n\n```json\n{\n  \"status\": true,\n  \"CHUNK_SIZE\": 1000,\n  \"CHUNK_OVERLAP\": 100,\n  \"RAG_TEMPLATE\": \"### Task:\\nRespond to the user query using the provided context...\\n<context>\\n{{CONTEXT}}\\n</context>\",\n  \"RAG_EMBEDDING_ENGINE\": \"\",\n  \"RAG_EMBEDDING_MODEL\": \"sentence-transformers/all-MiniLM-L6-v2\",\n  \"RAG_RERANKING_MODEL\": \"\",\n  \"RAG_EMBEDDING_BATCH_SIZE\": 1,\n  \"ENABLE_ASYNC_EMBEDDING\": true,\n  \"RAG_EMBEDDING_CONCURRENT_REQUESTS\": 0\n}\n```\n\n---\n\n## Disclosed Information and Its Value to an Attacker\n\n| Field | What it reveals |\n|---|---|\n| `RAG_EMBEDDING_ENGINE` | Backend type (OpenAI, Ollama, Azure, etc.) |\n| `RAG_EMBEDDING_MODEL` | Exact model name — reveals embedding model |\n| `RAG_RERANKING_MODEL` | Reranker in use — reveals reranker |\n| `RAG_TEMPLATE` | **RAG template** — exposes the RAG template |\n| `CHUNK_SIZE` / `CHUNK_OVERLAP` | Chunking parameters — enables exact reconstruction of how documents are split and retrieved |\n\n---\n\n## Attack Scenario\n\n1. Attacker sends one unauthenticated HTTP GET to `/api/v1/retrieval/`.\n2. Response reveals the embedding model and chunking parameters.\n3. Attacker uses the exact chunk size/overlap to craft RAG poisoning payloads that are guaranteed to be retrieved.\n\n---\n\n## Impact\n\n1. **RAG template disclosure**\n2. **Infrastructure fingerprinting** — embedding engine and model name reveal the AI stack to an internet scanner\n3. **RAG attack surface mapping** — chunk parameters enable precise calculation of retrieval boundaries\n4. **Zero-effort recon** — no brute force, no credentials, no rate-limit concern. Single request from any IP.\n\n---\n\n## Recommended Fix\n\nAdd `get_verified_user` dependency (or `get_admin_user` for stricter control):\n\n```python\n# BEFORE (vulnerable)\n@router.get('/')\nasync def get_status(request: Request):\n\n\n# AFTER\n@router.get('/')\nasync def get_status(request: Request, user=Depends(get_verified_user)):\n```",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "open-webui"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "0.9.5"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/open-webui/open-webui/security/advisories/GHSA-65pg-qhhw-mxwg"
  }, {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-45397"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/open-webui/open-webui"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/open-webui/open-webui/releases/tag/v0.9.5"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-306" ],
    "severity" : "MODERATE",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-05-14T20:26:34Z",
    "nvd_published_at" : "2026-05-15T21:16:37Z"
  }
}