Vulnerability Description
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.9, an authenticated LiteLLM Proxy caller with a valid virtual key can place api_base inside the user_config request body to bypass is_request_body_safe, which blocks top-level api_base and base_url but previously did not inspect or reject user_config. Because user_config constructs the outbound router, the nested destination redirects a server-side request to an internal or external host selected by the caller and can expose endpoints the caller cannot otherwise access. This issue is fixed in version 1.83.9.
Related Weaknesses (CWE)
References
- https://github.com/BerriAI/litellm/commit/47214be317f45a2d2ac08258362e0481411eb4
- https://github.com/BerriAI/litellm/pull/25827
- https://github.com/BerriAI/litellm/security/advisories/GHSA-hx8v-g79f-8w5f
FAQ
What is CVE-2026-59823?
CVE-2026-59823 is a documented vulnerability. LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.9, an authenticated LiteLLM Proxy caller with a valid virtual key can place api_base inside the user...
How severe is CVE-2026-59823?
CVSS scoring is not yet available for CVE-2026-59823. Check NVD for updates.
Is there a patch for CVE-2026-59823?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.