cve.bz

CVE-2026-47101 litellm litellm: Incorrect Authorization

8.7 highExploit referenceEPSS 1.2%Fix available

High (8.7) in litellm litellm. EPSS 1.2% estimated probability of exploitation activity in the next 30 days. Fixed in litellm 1.83.14.

On this page
LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit. When generating a key, the allowed_routes field is stored without verifying that the specified routes fall within the user's own permissions. A key created with access to admin-only routes can then be used to reach those routes successfully, bypassing the role-based access controls that would otherwise block the request, enabling full privilege escalation from internal_user to proxy_admin.

Severity

CVSS 4.0

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

CVSS 3.1

8.8 high
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
EPSS
1.2% (unchanged from 1.2% a week ago; 1.3% 30 days ago) estimated probability of exploitation activity in the next 30 days; 68th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: no · Technical impact: total, assessed 2026-05-22. 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-863 Incorrect Authorization
CWE-639 Authorization Bypass Through User-Controlled Key
OWASP Top 10
A01:2025 Broken Access Control
Published
Modified
NVD analysis
Analyzed, since modified
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-47101 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-47101?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-47101?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-2026-47101 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 CNA's record in the CVE List.

ProductAffected
BerriAI litellmbefore 1.83.14

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-qrc4-49gv-mv9mPyPIlitellm<1.83.141.83.14
PYSEC-2026-2598PyPIlitellm<1.83.141.83.14

Red Hat

Red Hat rates this Important.

Red Hat's statement

This vulnerability is rated Important because an authenticated LiteLLM proxy user with the internal_user role may be able to create API keys that grant access to admin-only routes, escalating privileges to proxy_admin level.

Exploitation requires network access to a LiteLLM proxy instance and valid credentials for a non-admin user account. Products that bundle litellm only as a client library, or that do not expose the LiteLLM proxy management API to untrusted users, have reduced exposure. Affected packages should be updated to litellm 1.83.14 or later when fixes are released.

Red Hat's mitigation

Update the litellm package to version 1.83.14 or later.

Until updated builds are available, restrict LiteLLM proxy deployments so only trusted administrators can access key-generation and management routes. Audit existing API keys for allowed_routes grants that exceed the creating user role, and rotate keys where unauthorized admin-route access is found.

ProductPackageStateAdvisory
Exploit Intelligenceexploit-intelligence-tech-preview/vulnerability-analysis-rhel9Affected
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-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-2026-47101.

GitHub PoC

Repositories on GitHub named after this CVE or listed for it by the PoC-in-GitHub index. For those marked Harbor Check: matches CVE, Flawharbor read the code and found it implements this CVE's exploitation technique: read, not run, and its dependencies only checked for warning signs, so a pointer and no guarantee. The rest are unverified: 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. How Harbor Check reads them, and what it found.

  • learner202649/CVE-2026-47101-PoC Harbor Check: matches CVE 0 stars, Shell, created
    The code for personally reproducing the corresponding vulnerability

References

Check your stackJSON