cve.bz

CVE-2026-114612 berriai litellm: Improper Privilege Management

9.9 criticalEPSS 0.3%Fix available

Critical (9.9) in berriai litellm. EPSS 0.3% estimated probability of exploitation activity in the next 30 days. Fixed in litellm 1.100.4, 1.101.3, 1.102.2.

On this page
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted metadata containing a forged administrator credential encrypted and returned by the API-key flow. Replaying that ciphertext as a bearer token causes the proxy to trust the forged proxy administrator identity, permitting administrative access and arbitrary commands through the MCP stdio endpoint. Versions 1.87.0 through 1.90.x require EXPERIMENTAL_UI_LOGIN to be enabled, while versions after 1.91.0 are exploitable in the default configuration. This issue was fixed in LiteLLM 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2.

Severity

CVSS 3.1

9.9 critical
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
EPSS
0.3% (unchanged from 0.3% a week ago) estimated probability of exploitation activity in the next 30 days; 25th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: no · Technical impact: total, assessed 2026-10-30. 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-269 Improper Privilege Management
CWE-345 Insufficient Verification of Data Authenticity
CWE-441 Unintended Proxy or Intermediary (Confused Deputy)
OWASP Top 10
A01:2025 Broken Access Control, A06:2025 Insecure Design, A08:2025 Software or Data Integrity Failures
Published
Modified
NVD analysis
Awaiting analysis
Record from
the NVD, synced

Fix and patched versions

  • litellm (PyPI): fixed in 1.100.4, 1.101.3, 1.102.2, 1.103.1, 1.104.0rc2

Ask an AI about this CVE

Show the promptExplain CVE-2026-114612 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-114612?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-114612?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-2026-114612 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 litellm>= 1.87.0, < 1.100.4
BerriAI litellm>= 1.101.0, < 1.101.3
BerriAI litellm>= 1.102.0, < 1.102.2
BerriAI litellm>= 1.103.0, < 1.103.1
BerriAI litellm>= 1.104.0-rc.1, < 1.104.0-rc.2

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-7hp6-4w63-5g45PyPIlitellm>=1.91.0 <1.100.41.100.4
GHSA-7hp6-4w63-5g45PyPIlitellm>=1.101.0 <1.101.31.101.3
GHSA-7hp6-4w63-5g45PyPIlitellm>=1.102.0 <1.102.21.102.2
GHSA-7hp6-4w63-5g45PyPIlitellm>=1.103.0 <1.103.11.103.1
GHSA-7hp6-4w63-5g45PyPIlitellm>=1.104.0rc1 <1.104.0rc21.104.0rc2

Red Hat

Red Hat rates this Critical.

Red Hat's statement

Critical severity reflects the high blast radius of this vulnerability, as an authenticated user can forge administrative session tokens over the network and execute arbitrary system commands via exposed proxy endpoints. Red Hat products evaluated against this issue do not incorporate the affected LiteLLM code and are not impacted. Standalone deployments of the LiteLLM proxy remain susceptible when user-supplied metadata is encrypted with the same key used for session validation.

ProductPackageStateAdvisory
Exploit Intelligenceexploit-intelligence/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-2026-114612.

Attack patterns (CAPEC)

  • CAPEC-219 XML Routing Detour Attacks Likelihood: High · Severity: Medium
  • CAPEC-465 Transparent Proxy Abuse Severity: Medium
  • CAPEC-58 Restful Privilege Elevation Likelihood: High · Severity: High
  • CAPEC-122 Privilege Abuse Likelihood: High · Severity: Medium
  • CAPEC-233 Privilege Escalation

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-345 (12).

References

Check your stackJSON