Browse / AI Framework and Platform Flaws / CVE-2026-59823
LiteLLM Proxy has server-side request forgery via the `user_config` request parameter
- Class
- AI Framework and Platform Flaws (filed by a model that read the advisory)
- Technique
- Server-side request forgery
- Affected
- litellm (PyPI)
- Gets past
- SSRF protection
- CVSS
- CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:L/SI:N/SA:N
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
Nesting an api_base inside user_config slips past a check that only inspects top-level keys, so the proxy sends requests to hosts the caller chooses. (Our summary, written by a model. The source text is below.)
Details
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).
References
- https://github.com/BerriAI/litellm/security/advisories/GHSA-hx8v-g79f-8w5f
- https://nvd.nist.gov/vuln/detail/CVE-2026-59823
- https://github.com/BerriAI/litellm/pull/25827
- https://github.com/BerriAI/litellm/commit/47214be317f45a2d2ac08258362e0481411eb427
- https://github.com/BerriAI/litellm
Source: GitHub Advisory Database, used under CC BY 4.0.