LiteLLM 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.
Weakness
The product does not properly assign, modify, track, or check privileges for an actor, creating an unintended sphere of control for that actor.
Potential Mitigations
Related Attack Patterns
- https://cwe.mitre.org/data/definitions/122.html
- https://cwe.mitre.org/data/definitions/233.html
- https://cwe.mitre.org/data/definitions/58.html
References
- https://github.com/BerriAI/litellm/commit/1d5fdc87fed66b49e1df8cf7d708ad93249eb7d0
- https://github.com/BerriAI/litellm/commit/9161d7f9d6073603ba61ee4aa5e2c0ef5b37a81b
- https://github.com/BerriAI/litellm/commit/9fa1a641119dd0d4fe43e93622eae5f482ceb63f
- https://github.com/BerriAI/litellm/commit/a80eacacee118fbed54e3d98f239d17a63fac818
- https://github.com/BerriAI/litellm/commit/f7cd90f09e9716652b38daec9f0640cdf49d582b
- https://github.com/BerriAI/litellm/releases/tag/v1.100.4
- https://github.com/BerriAI/litellm/releases/tag/v1.101.3
- https://github.com/BerriAI/litellm/releases/tag/v1.102.2
- https://github.com/BerriAI/litellm/releases/tag/v1.103.1
- https://github.com/BerriAI/litellm/releases/tag/v1.104.0-rc.2
- https://github.com/BerriAI/litellm/security/advisories/GHSA-7hp6-4w63-5g45