CVSS 3.1
9.9 criticalCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:HCritical (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.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:Hlitellm (PyPI): fixed in 1.100.4, 1.101.3, 1.102.2, 1.103.1, 1.104.0rc2Explain 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.
From the CNA's record in the CVE List.
| Product | Affected |
|---|---|
| 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 |
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-7hp6-4w63-5g45 | PyPI | litellm | >=1.91.0 <1.100.4 | 1.100.4 |
| GHSA-7hp6-4w63-5g45 | PyPI | litellm | >=1.101.0 <1.101.3 | 1.101.3 |
| GHSA-7hp6-4w63-5g45 | PyPI | litellm | >=1.102.0 <1.102.2 | 1.102.2 |
| GHSA-7hp6-4w63-5g45 | PyPI | litellm | >=1.103.0 <1.103.1 | 1.103.1 |
| GHSA-7hp6-4w63-5g45 | PyPI | litellm | >=1.104.0rc1 <1.104.0rc2 | 1.104.0rc2 |
Red Hat rates this Critical.
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.
| Product | Package | State | Advisory |
|---|---|---|---|
| Exploit Intelligence | exploit-intelligence/vulnerability-analysis-rhel9 | Not affected | |
| Lightspeed Core | lightspeed-core/lightspeed-stack-rhel9 | Not affected | |
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-26/lightspeed-chatbot-rhel9 | Not affected | |
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-27/lightspeed-chatbot-rhel9 | Not affected | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-llama-stack-core-rhel9 | Not affected | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-mlflow-rhel9 | Not affected | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-th-torch-cpu-py312-rhel9 | Not affected | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-th-torch-cuda-py312-rhel9 | Not affected | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9 | Not 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.
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).