CVE-2026-35029 — LiteLLM affected by privilege escalation via unrestricted proxy configuration endpoint

Description (CNA)

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, the /config/update endpoint does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to modify proxy configuration and environment variables, register custom pass-through endpoint handlers pointing to attacker-controlled Python code, achieving remote code execution, read arbitrary server files by setting UI_LOGO_PATH and fetching via /get_image, and take over other privileged accounts by overwriting UI_USERNAME and UI_PASSWORD environment variables. Fixed in v1.83.0.

Affected (CNA)

Vendor / product	Versions
BerriAI / litellm	affected < 1.83.0

CWE

CWE-863

References

https://github.com/BerriAI/litellm/security/advisories/GHSA-53mr-6c8q-9789

ADP enrichment

CISA-ADP

No English description supplied.

No references supplied.

CVE

No English description supplied.

http://seclists.org/fulldisclosure/2026/Apr/17

redhat-SADP

A flaw was found in LiteLLM, an AI Gateway proxy server. An authenticated user can exploit a missing authorization check on the `/config/update` endpoint. This allows the user to modify proxy configurations and environment variables, leading to remote code execution by registering custom endpoint handlers. Additionally, this vulnerability enables unauthorized reading of server files and potential takeover of privileged accounts through environment variable manipulation.