CVE-2026-84377
Description
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.
How to fix
- litellm1.88.6, 1.89.7, 1.90.7, 1.91.5, 1.92.2, 1.93.2, 1.94.3, 1.95.1, 1.96.2 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| litellmPyPI | v < 1.88.6, 1.89.0 ≤ v < 1.89.7, 1.90.0 ≤ v < 1.90.7, 1.91.0 ≤ v < 1.91.5, 1.92.0 ≤ v < 1.92.2, 1.93.0 ≤ v < 1.93.2, 1.94.0 ≤ v < 1.94.3, 1.95.0 ≤ v < 1.95.1, 1.96.0 ≤ v < 1.96.2 | 1.88.6, 1.89.7, 1.90.7, 1.91.5, 1.92.2, 1.93.2, 1.94.3, 1.95.1, 1.96.2 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.