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

Severity: high (CVSS 8.8 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 38.6% probability of exploitation in the next 30 days
Public exploit or detection template: yes
Published: 2026-04-06 · updated 2026-10-23
Weakness: CWE-863

Description

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 products

BerriAI litellm: before 1.83.0 — fixed in 1.83.0

How to fix

Upgrade to a fixed version: BerriAI litellm 1.83.0. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2026-35029 or the next vulnerability affects your stack