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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
litellmPyPI | < 1.83.0 | 1.83.0 |
Affected products
7- osv-coords6 versionspkg:apk/chainguard/airflow-2pkg:apk/chainguard/airflow-3pkg:apk/chainguard/litellmpkg:apk/chainguard/litellm-compatpkg:apk/wolfi/airflow-3pkg:pypi/litellm
< 2.11.2-r7+ 5 more
- (no CPE)range: < 2.11.2-r7
- (no CPE)range: < 3.1.8-r11
- (no CPE)range: < 1.83.3.0-r0
- (no CPE)range: < 1.83.3.0-r0
- (no CPE)range: < 3.1.8-r11
- (no CPE)range: < 1.83.0
Patches
Vulnerability mechanics
References
3- github.com/BerriAI/litellm/security/advisories/GHSA-jjhc-v7c2-5hh6nvdVendor AdvisoryMitigationWEB
- github.com/advisories/GHSA-jjhc-v7c2-5hh6ghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-35030ghsaADVISORY
News mentions
0No linked articles in our index yet.