CVE-2026-84377

published 2 Sep 2026 · updated 3 Sep 2026

LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters

6.5MediumCVSS 6.5EPSS 1%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 1%. No fixed version is recorded.

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination the user controls and cause the proxy to send its configured provider credentials to that destination. Request validation in litellm/proxy/auth/auth_utils.py, litellm/proxy/common_request_processing.py, litellm/proxy/health_endpoints/_health_endpoints.py, litellm/proxy/image_endpoints/endpoints.py, and litellm/proxy/litellm_pre_call_utils.py used incomplete checks that did not cover every sensitive parameter or inspect equivalent values across nested request fields, path values, and bracket-notation form data. Routing and credential parameters including api_base, base_url, model_list, fallbacks, and litellm_credential_name could therefore be applied without clearing the operator's stored key, exposing upstream provider credentials and other configured secrets and permitting server-side requests to internal services reachable by the proxy. This issue is fixed in versions 1.88.6 and 1.96.2.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
BerriAILiteLLM<1.88.6, >=1.89.0 <1.96.2

Timeline

Every event on this vulnerability

Related

Other vulnerabilities in LiteLLM, strongest first

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-84377 severity on Zeptric[![CVE-2026-84377](https://zeptric.io/badge/cve/CVE-2026-84377.svg)](https://zeptric.io/cve/CVE-2026-84377)