VYPR
Get started
← All advisories
Critical severity9.1NVD Advisory· Published Apr 6, 2026· Updated Apr 7, 2026

CVE-2026-35030

CVE-2026-35030

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.

Affected packages

Versions sourced from the GitHub Security Advisory.

PackageAffected versionsPatched versions
litellmPyPI
< 1.83.01.83.0

Affected products

1
  • Litellm/Litellm
    cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*
    Range: <1.83.0

Patches

0

No patches discovered yet.

Vulnerability mechanics

AI mechanics synthesis has not run for this CVE yet.

References

3

News mentions

16