LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.
| Vendor | Product | Versions |
|---|---|---|
| berriai | litellm | < 1.84.0 |
Downstream vendors/products affected by this vulnerability
| Vendor | Product | Source | Confidence |
|---|---|---|---|
| open source | litellm | cert_advisory | 90% |
Loading…
Updated vendor to BerriAI, product to litellm, severity to CRITICAL, and affected versions to 1.83.x, with a new description detailing the vulnerability.
Initial creation
