CVE-2026-35030

9.4 critical exploit SSVC exploitation: none Modified

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.

Fix

Public exploits 1

learner202649/CVE-2026-35030-PoC PoC on GitHub

Each line links to the index that lists it, never to exploit code. Exploit-DB's "verified" and a Metasploit rank of good or better count as verified; a PoC-in-GitHub entry is a repository's claim.

Patch, vendor advisory and mitigation references on NVD 1

https://github.com/BerriAI/litellm/security/advisories/GHSA-jjhc-v7c2-5hh6 Mitigation, Vendor Advisory

Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.

CVE-2026-35030

Fix

Public exploits 1

Patch, vendor advisory and mitigation references on NVD 1

Change history 1

Affected (CPE criteria) 1

References 7