Skip to content
Threat Brief

← All advisories

CVE-2026-35030

Critical 9.4No known exploitationFix available

LiteLLM has an authentication bypass via OIDC userinfo cache key collision

Vendor advisory: GHSA-jjhc-v7c2-5hh6

Record last updated

CVSS score

9.4

Critical on a 0 to 10 scale

EPSS, chance of exploitation in 30 days

None

No EPSS score available

CISA remediation deadline

None

Not in the KEV catalog

Description

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.

Weakness: CWE-287

Patching and mitigation

Patch status
Fix available (source: GitHub Advisory Database)
Fix documented (source date)
Mitigation
None documented
Vendor guidance
access.redhat.com (opens in a new tab)

Affected products

VendorProductAffected versionsFixed inPer
BerriAIlitellm< 1.83.0Not documentedCVE Program
piplitellmall versions before 1.83.01.83.0GitHub Advisory Database

Timeline

  1. Disclosure

    CVE record published by GitHub_M

    Source: CVE Program (opens in a new tab)

  2. Patch

    Fix documented by GitHub Advisory Database

    Source: GitHub Advisory Database (opens in a new tab)

Vendor guidance and references