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 products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| BerriAI | litellm | < 1.83.0 | — |
Fixed in Linux distributions
Distributions backport fixes, so the version that fixes this vulnerability differs per release — upgrade to at least the version shown. From the distributions' security trackers and advisories.
Wolfi
| Release | Package | Fixed in | Advisory |
|---|---|---|---|
| Wolfi rolling | airflow-3 | 3.1.8-r11 | — |
Public exploits
Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.
GitHub 1 repository
-
learner202649/CVE-2026-35030-PoC ★ 0 · May 19, 2026
The code for personally reproducing the corresponding vulnerability
Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | litellm | < 1.83.0 | 1.83.0 | GHSA-jjhc-v7c2-5hh6 |