Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · LiteLLM

CVE-2026-59823: LiteLLM Proxy has server-side request forgery via the `user_config` request parameter

mediumCVSS 4.0 5.3GHSA-hx8v-g79f-8w5f

Summary A server-side request forgery in LiteLLM Proxy lets an authenticated caller redirect the proxy's outbound request to a host of their choosing by smuggling an apibase inside the userconfig request body, bypassing the existing parameter guard. Details LiteLLM Proxy validates request bodies with isrequestbodysafe, which blocks the apibase and baseurl parameters but does not cover userconfig.

Published Sep 17, 2026

Affected packages

litellm

Ecosystem
PyPI
Affected
<= 1.83.8
Fixed in
1.83.9
Check
pip show litellm

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Summary

A server-side request forgery in LiteLLM Proxy lets an authenticated caller redirect the proxy's outbound request to a host of their choosing by smuggling an api_base inside the user_config request body, bypassing the existing parameter guard.

Details

LiteLLM Proxy validates request bodies with is_request_body_safe, which blocks the api_base and base_url parameters but does not cover user_config. The user_config object is used to build the outbound router for a request, so a caller can place an api_base inside it and reach an arbitrary host. The guard only inspected the two top-level keys, so the same api_base nested inside user_config was never checked.

Exploitation requires a valid virtual key.

Impact

An authenticated caller can make the proxy issue server-side requests to internal or external hosts of their choosing, reaching endpoints the caller cannot otherwise access.

Affected / Patched

Affected: <= 1.83.8 Patched: 1.83.9

Remediation

Upgrade to 1.83.9 or later (released 2026-04-17).

Credited to brettgus.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More LiteLLM vulnerabilities

All LiteLLM entries