JWT Cache Key Collision in LiteLLM <=1.82 (BerriAI)
CVE-2026-35030 Published on April 6, 2026

LiteLLM has an authentication bypass via OIDC userinfo cache key collision
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.

NVD

Vulnerability Analysis

CVE-2026-35030 is exploitable with network access, and does not require authorization privileges or user interaction. This vulnerability is considered to have a low attack complexity. The potential impact of an exploit of this vulnerability is considered to have a high impact on confidentiality and integrity, and no impact on availability.

Attack Vector:
NETWORK
Attack Complexity:
LOW
Privileges Required:
NONE
User Interaction:
NONE
Scope:
UNCHANGED
Confidentiality Impact:
HIGH
Integrity Impact:
HIGH
Availability Impact:
NONE

Weakness Types

What is an authentification Vulnerability?

When an actor claims to have a given identity, the software does not prove or insufficiently proves that the claim is correct.

CVE-2026-35030 has been classified to as an authentification vulnerability or weakness.

Truncation of Security-relevant Information

The application truncates the display, recording, or processing of security-relevant information in a way that can obscure the source or nature of an attack.


Products Associated with CVE-2026-35030

Want to know whenever a new CVE is published for Red Hat products? stack.watch will email you.

Red Hat Ansible Automation Platform
 
Red Hat Openshift Ai
 
Red Hat Lightspeed Core
 

Affected Versions

BerriAI litellm: Red Hat Ansible Automation Platform 2.6: Red Hat OpenShift AI 2.25: Red Hat OpenShift AI 3.3: Red Hat Lightspeed Core: Red Hat OpenShift AI (RHOAI):

Exploit Probability

EPSS
0.40%
Percentile
31.14%

EPSS (Exploit Prediction Scoring System) scores estimate the probability that a vulnerability will be exploited in the wild within the next 30 days. The percentile shows you how this score compares to all other vulnerabilities.