LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLMs 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.
Weakness
When an actor claims to have a given identity, the product does not prove or insufficiently proves that the claim is correct.
Affected Software
| Name | Vendor | Start Version | End Version |
|---|---|---|---|
| Litellm | Litellm | * | 1.84.0 (excluding) |
Potential Mitigations
Related Attack Patterns
- https://cwe.mitre.org/data/definitions/114.html
- https://cwe.mitre.org/data/definitions/115.html
- https://cwe.mitre.org/data/definitions/151.html
- https://cwe.mitre.org/data/definitions/194.html
- https://cwe.mitre.org/data/definitions/22.html
- https://cwe.mitre.org/data/definitions/57.html
- https://cwe.mitre.org/data/definitions/593.html
- https://cwe.mitre.org/data/definitions/633.html
- https://cwe.mitre.org/data/definitions/650.html
- https://cwe.mitre.org/data/definitions/94.html