GHSA-HP5M-24VP-VQ2Q
Vulnerability from github – Published: 2026-05-08 19:45 – Updated: 2026-05-15 23:52Summary
The /responses endpoint in the OpenAI router accepts any authenticated user and forwards requests directly to upstream LLM providers without enforcing per-model access control. While the primary chat completion endpoint (generate_chat_completion) checks model ownership, group membership, and AccessGrants before allowing a request, the /responses proxy only validates that the user has a valid session via get_verified_user.
This allows any authenticated user — regardless of role or group assignment — to interact with any model configured on the instance by sending a POST request to /api/openai/responses with an arbitrary model ID.
Impact
As per OWASP TOP 10 LLM:
-
Model Denial of Service (OWASP LLM04): An unauthorized user can submit resource-intensive requests to expensive models (e.g., o1-pro, GPT-4o) that were explicitly restricted by the administrator. In shared deployments, this can exhaust API budgets or rate limits, causing total service disruption for all legitimate users.
-
Model Theft (OWASP LLM10): If the instance proxies access to fine-tuned or self-hosted models, unauthorized users can freely interact with them, enabling capability extraction or model distillation without authorization.
-
Access Policy Bypass: Administrators lose the ability to enforce cost-tier restrictions, team-based model assignments, or compliance boundaries through the existing access control system.
The endpoint is a raw passthrough proxy and does not resolve workspace model configurations (system prompts, knowledge bases, RAG pipelines). Therefore, workspace-specific confidential data is not directly exposed through this vector.
PR: https://github.com/open-webui/open-webui/pull/23481
{
"affected": [
{
"database_specific": {
"last_known_affected_version_range": "\u003c= 0.8.12"
},
"package": {
"ecosystem": "PyPI",
"name": "open-webui"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.9.0"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2026-44556"
],
"database_specific": {
"cwe_ids": [
"CWE-284",
"CWE-862"
],
"github_reviewed": true,
"github_reviewed_at": "2026-05-08T19:45:53Z",
"nvd_published_at": "2026-05-15T20:16:47Z",
"severity": "HIGH"
},
"details": "## Summary\n\nThe /responses endpoint in the OpenAI router accepts any authenticated user and forwards requests directly to upstream LLM providers without enforcing per-model access control. While the primary chat completion endpoint (generate_chat_completion) checks model ownership, group membership, and AccessGrants before allowing a request, the /responses proxy only validates that the user has a valid session via get_verified_user.\n\nThis allows any authenticated user \u2014 regardless of role or group assignment \u2014 to interact with any model configured on the instance by sending a POST request to /api/openai/responses with an arbitrary model ID.\n\n## Impact\n\nAs per OWASP TOP 10 LLM:\n\n- **Model Denial of Service (OWASP LLM04):** An unauthorized user can submit resource-intensive requests to expensive models (e.g., o1-pro, GPT-4o) that were explicitly restricted by the administrator. In shared deployments, this can exhaust API budgets or rate limits, causing total service disruption for all legitimate users.\n\n- **Model Theft (OWASP LLM10):** If the instance proxies access to fine-tuned or self-hosted models, unauthorized users can freely interact with them, enabling capability extraction or model distillation without authorization.\n\n- **Access Policy Bypass:** Administrators lose the ability to enforce cost-tier restrictions, team-based model assignments, or compliance boundaries through the existing access control system.\n\nThe endpoint is a raw passthrough proxy and does not resolve workspace model configurations (system prompts, knowledge bases, RAG pipelines). Therefore, workspace-specific confidential data is not directly exposed through this vector.\n\nPR: https://github.com/open-webui/open-webui/pull/23481",
"id": "GHSA-hp5m-24vp-vq2q",
"modified": "2026-05-15T23:52:36Z",
"published": "2026-05-08T19:45:53Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-hp5m-24vp-vq2q"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-44556"
},
{
"type": "WEB",
"url": "https://github.com/open-webui/open-webui/pull/23481"
},
{
"type": "PACKAGE",
"url": "https://github.com/open-webui/open-webui"
}
],
"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:H",
"type": "CVSS_V3"
}
],
"summary": "Open WebUI\u0027s responses passthrough endpoint lacks access control authorization"
}
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.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.