← back
CVE-2026-35030criticalCWE-222CWE-287

LiteLLM has an authentication bypass via OIDC userinfo cache key collision

48Vexday Risk Score

No sign of exploitation. It has a public proof of concept.

ssvc Attendcvss 9.4epss 0.5%
from disclosure to weapon43 days
Published on NVDApr 6
1st PoC+43d
exploitation probability
0.5%top 60% of all CVEs
observed exploitation
nono source reports it
1 public exploit(s)
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.
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N
Affected products
BerriAI · litellm
⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.