{"id":"CVE-2026-44556","aliases":["GHSA-hp5m-24vp-vq2q","PYSEC-2026-2734"],"title":"Open WebUI's responses passthrough endpoint lacks access control authorization","summary":"Open WebUI's responses passthrough endpoint lacks access control authorization","severity":"high","cvss":7.1,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:H","vendor":"open-webui","product":"open-webui","ecosystem":"pip","affected":["open-webui < 0.9.0"],"patched":["open-webui 0.9.0"],"published":"2026-05-08","updated":"2026-07-13","source":"OSV","sourceUrl":"https://osv.dev/vulnerability/GHSA-hp5m-24vp-vq2q","references":[{"url":"https://github.com/open-webui/open-webui/security/advisories/GHSA-hp5m-24vp-vq2q"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-44556"},{"url":"https://github.com/open-webui/open-webui/pull/23481"},{"url":"https://github.com/open-webui/open-webui"}],"tags":["osv","pip"],"epss":0.00306,"epssPercentile":0.23534,"ingestedAt":"2026-07-13T18:57:59.283Z","slug":"CVE-2026-44556","body":"## Overview\n\n## 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 — 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.\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\n\n## Affected packages\n\n- `open-webui < 0.9.0`\n\n## Remediation\n\nUpgrade to a patched release:\n\n- `open-webui 0.9.0`","depth":"twilight","depthScore":39,"depthScoreParts":{"impact":39.1,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}