LiteLLM admin auth bypass via reused cryptographic context
BerriAI litellm
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| litellm PyPI |
|
|
BerriAI litellm
| Product | Affected | Fixed in |
|---|---|---|
| litellm PyPI |
|
|
1.103.11.104.0rc2LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted metadata containing a forged administrator credential encrypted and returned by the API-key flow. Replaying that ciphertext as a bearer token causes the proxy to trust the forged proxy administrator identity, permitting administrative access and arbitrary commands through the MCP stdio endpoint. Versions 1.87.0 through 1.90.x require EXPERIMENTAL_UI_LOGIN to be enabled, while versions after 1.91.0 are exploitable in the default configuration. This issue was fixed in LiteLLM 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2.
From the CVE record · GitHub_M
The LiteLLM proxy reuses a cryptographic context for stored secrets and session tokens. An authenticated internal user can use crafted metadata in the API-key flow to forge an administrator bearer token, gaining administrative access and the ability to run arbitrary commands through the MCP stdio endpoint. Versions 1.87.0 through 1.90.x require EXPERIMENTAL_UI_LOGIN to be enabled; affected versions from 1.91.0 are exploitable in the default configuration.
Teams running the PyPI litellm package should check versions >=1.91.0 <1.100.4, >=1.101.0 <1.101.3, >=1.102.0 <1.102.2, >=1.103.0 <1.103.1, or >=1.104.0rc1 <1.104.0rc2, as well as versions 1.87.0 through 1.90.x if EXPERIMENTAL_UI_LOGIN is enabled.