Skip to content
Fencer Vulns
critical 9.1

CVE-2026-35030 json

LiteLLM has an authentication bypass via OIDC userinfo cache key collision

published 2026-04-03 7 mo ago modified 2026-10-24 16 d ago also EUVD-2026-19372 , GHSA-jjhc-v7c2-5hh6 , PYSEC-2026-390

cvss
9.1
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.6%
EPSS 0.6% chance of exploitation in 30 days, percentile 50%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi litellm 1.83.0
  • Red Hat Red Hat Ansible Automation Platform 2.6 1777398576
  • Red Hat Red Hat OpenShift AI 2.25 1781826406
  • Red Hat Red Hat OpenShift AI 3.3 1782310008

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-35030 updated cvss 9.1

litellm: LiteLLM: Authentication bypass and privilege escalation via OIDC userinfo cache key collision

  • Red Hat Lightspeed Core redhat-user-workloads/lightspeed-core-tenant/lightspeed-stack Red Hat Ansible Automation Platform 2 redhat-user-workloads/ansible-tenant/ansible-automation-platform-26/lightspeed-chatbot-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-mlflow-rhel9
    affected: workaround, no fix available
  • Red Hat Ansible Automation Platform 2.6 ansible-automation-platform-26 1777398576
    fixed: vendor fix RHSA-2026:13545
  • Red Hat OpenShift AI 2.25 rhoai/odh-llama-stack-core-rhel9 1781826406
    fixed: vendor fix RHSA-2026:28960
  • Red Hat OpenShift AI 3.3 rhoai/odh-llama-stack-core-rhel9 1782310008
    fixed: vendor fix RHSA-2026:30056
  • Red Hat Ansible Automation Platform 2.6 ansible-automation-platform 1777410604, ansible-automation-platform 1777410621, ansible-automation-platform-26 1777163004, ansible-automation-platform-26 1777163348, ansible-automation-platform-26 1777163557, ansible-automation-platform-26 1777163594, +23 more Red Hat OpenShift AI 2.25 rhoai/odh-rhel9-operator 1782131177, rhoai/odh-operator-bundle 1782131953 Red Hat OpenShift AI 3.3 rhoai/odh-rhel9-operator 1782332088, rhoai/odh-operator-bundle 1782332801
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
yes
Technical impact
total
Assessed
7 mo ago

Exploit prediction

0.64% chance of exploitation in the next 30 days, higher than 50% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 4.0 9.4 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
CISA ADP 3.1 9.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
CNA 4.0 9.4 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CNA 3.1 9.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N

Affected packages

ecosystem package affected fixed in
pypi litellm
<1.83.0
1.83.0

Affected products

  • BerriAI litellm
  • Red Hat Red Hat Ansible Automation Platform 2.6
  • Red Hat Red Hat OpenShift AI 2.25
  • Red Hat Red Hat OpenShift AI 3.3
  • Red Hat Lightspeed Core
  • Red Hat Red Hat OpenShift AI (RHOAI)

Classification

Weakness
  • CWE-287 Improper Authentication
  • CWE-222 Truncation of Security-relevant Information

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.