---
id: CVE-2026-35030
title: >-
  LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native)
  format
summary: >-
  LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native)
  format. Prior to 1.83.0, when JWT authentication is enabled (enable_jwt_auth:
  true), the OIDC userinfo cache uses token[:20] as the cache key. JWT headers
  prod…
severity: critical
cvss: 9.1
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N'
cwe:
  - CWE-287
  - CWE-222
vendor: litellm
product: litellm
affected:
  - litellm < 1.83.0
patched:
  - litellm 1.83.0
published: '2026-04-06'
updated: '2026-07-15'
sourceUpdated: '2026-07-15T02:20:40.403'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-35030'
references:
  - url: 'https://github.com/BerriAI/litellm/security/advisories/GHSA-jjhc-v7c2-5hh6'
    label: security-advisories@github.com
  - url: 'https://access.redhat.com/errata/RHSA-2026:13545'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:28960'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:30056'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/security/cve/CVE-2026-35030'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2455509'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-35030.json
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
tags:
  - nvd
  - cve.org
  - exploit-available
ssvc:
  exploitation: none
  automatable: 'yes'
  technicalImpact: total
  timestamp: '2026-04-07T14:24:02.117235Z'
scores:
  nvd: 9.1
  cna: 9.4
ingestedAt: '2026-09-14T11:45:19.214Z'
epss: 0.00879
epssPercentile: 0.5744
exploits:
  github: 1
  githubRepos:
    - 'https://github.com/learner202649/CVE-2026-35030-PoC'
  checkedAt: '2026-09-27T10:33:45.385Z'
exploitAvailable: true
---

## Overview

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, when JWT authentication is enabled (enable_jwt_auth: true), the OIDC userinfo cache uses token[:20] as the cache key. JWT headers produced by the same signing algorithm generate identical first 20 characters. This configuration option is not enabled by default. Most instances are not affected. An unauthenticated attacker can craft a token whose first 20 characters match a legitimate user's cached token. On cache hit, the attacker inherits the legitimate user's identity and permissions. This affects deployments with JWT/OIDC authentication enabled. Fixed in v1.83.0.

## Affected

- `litellm < 1.83.0`

## Remediation

Upgrade past the affected range:

- `litellm 1.83.0`