cve.bz

CVE-2026-59822 BerriAI LiteLLM Improper Authentication Vulnerability

8.8 highKEVEPSS 0.8%Fix available

High (8.8) in BerriAI LiteLLM. In CISA KEV since 2026-09-02. EPSS 0.8% estimated probability of exploitation activity in the next 30 days. Fixed in litellm 1.84.0.

On this page
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.

Severity

CVSS 4.0

8.8 high
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N

CVSS 3.1

8.2 high
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
EPSS
0.8% (unchanged from 0.8% a week ago; 0.8% 30 days ago) estimated probability of exploitation activity in the next 30 days; 58th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA KEV
listed 2026-09-02, due 2026-09-16
CISA's assessment (SSVC)
Exploitation: active · Automatable: yes · Technical impact: partial, assessed 2026-09-02. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWEs
CWE-287 Improper Authentication
CWE-306 Missing Authentication for Critical Functionality
OWASP Top 10
A07:2025 Authentication Failures
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-59822 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-59822?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-59822?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-59822 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
litellm:litellmbefore 1.84.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-7488-6r32-c95qPyPIlitellm<1.84.01.84.0
PYSEC-2026-3479PyPIlitellm<1.84.01.84.0

Red Hat

Red Hat rates this Important.

Red Hat's statement

affects LiteLLM proxy deployments prior to 1.84.0 where the MCP Streamable HTTP endpoint is exposed. Red Hat products that include LiteLLM as a Python dependency— including Red Hat OpenShift AI (odh-mlflow-rhel9 and similar images), Red Hat Ansible Automation Platform Lightspeed chatbot images (lightspeed-chatbot-rhel9, ansible-chatbot-stack), and Red Hat Exploit Intelligence (vulnerability-analysis-rhel9)—are not affected in their default configurations because they do not start the LiteLLM proxy server or expose its MCP HTTP authentication path. These images run services such as MLflow, Lightspeed Core (lightspeed_stack.py), or vulnerability analysis workloads and use LiteLLM only as a client library or transitive dependency. The vulnerable execute path is reachable only when LiteLLM proxy is explicitly deployed with MCP routes enabled.

Red Hat's mitigation

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.

ProductPackageStateAdvisory
Exploit Intelligenceexploit-intelligence-tech-preview/vulnerability-analysis-rhel9Not affected
Lightspeed Corelightspeed-core/lightspeed-stack-rhel9Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-26/lightspeed-chatbot-rhel9Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-27/lightspeed-chatbot-rhel9Not affected
Red Hat OpenShift AI (RHOAI)rhoai/odh-llama-stack-core-rhel9Not affected
Red Hat OpenShift AI (RHOAI)rhoai/odh-mlflow-rhel9Not affected
Red Hat OpenShift AI (RHOAI)rhoai/odh-th-torch-cpu-py312-rhel9Not affected
Red Hat OpenShift AI (RHOAI)rhoai/odh-th-torch-cuda-py312-rhel9Not affected
Red Hat OpenShift AI (RHOAI)rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9Not affected

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-59822.

GitHub PoC (unverified)

Repositories on GitHub named after this CVE. Nobody has checked them and they are not scanned: some hold a working proof of concept, some nothing useful, and some malware made to look like one. Read the code before you run any of it.

Attack patterns (CAPEC)

  • CAPEC-12 Choosing Message Identifier Likelihood: High · Severity: High
  • CAPEC-36 Using Unpublished Interfaces or Functionality Likelihood: Medium · Severity: High
  • CAPEC-62 Cross Site Request Forgery Likelihood: High · Severity: Very High
  • CAPEC-166 Force the System to Reset Values Severity: Medium
  • CAPEC-216 Communication Channel Manipulation
  • CAPEC-22 Exploiting Trust in Client Likelihood: High · Severity: High
  • CAPEC-57 Utilizing REST's Trust in the System Resource to Obtain Sensitive Data Likelihood: Medium · Severity: Very High
  • CAPEC-94 Adversary in the Middle (AiTM) Likelihood: High · Severity: Very High
  • CAPEC-114 Authentication Abuse Severity: Medium
  • CAPEC-115 Authentication Bypass Severity: Medium

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-287.

References

Check your stackJSON