CVE
CVE-2026-42271
BerriAI · litellm; Red Hat · Red Hat OpenShift AI 2.25; +2 more
- First Reported
- Mar 16, 2026
- Latest Reported
- Nov 16, 2026
CVE Enrichment
- CVSS
- 8.7 HIGH
- EPSS
- 91.45%
- EPSS Percentile
- 99.81%
- CISA KEV
- YES — Known Exploited Vulnerability
Description
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process. The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host. This issue has been patched in version 1.83.7.
Technical Details
- CVSS Version
- 4.0
- CNA / NVD Source
- [email protected]
- Published
- 08-May-2026 11:16
- Last Modified
- 27-Oct-2026 03:10
- EPSS Date
- 2026-11-09
- CWE
- CWE-77, CWE-78
CVSS Vector
CVSS:4.0 AV:N /
AC:L /
AT:P /
PR:L /
UI:N /
VC:H /
VI:H /
VA:H /
SC:H /
SI:N /
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
CISA KEV Details
- Date Added
- 2026-06-08
- Remediation Due
- 2026-06-22
- Known Ransomware Campaign Use
- Unknown
- Required Action
- Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
- Notes
- This vulnerability affects a common open-source component, third-party library, or a protocol used by different products. Please check with specific vendors for information on patching status. For more information, please see: https://github.com/BerriAI/litellm/security/advisories/GHSA-v4p8-mg3p-g94g ; https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable ; https://nvd.nist.gov/vuln/detail/CVE-2026-42271
CNA Products / Version Status
- Red Hat · Exploit Intelligence
Source: CNA · 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Default status: unaffected
CPEs: cpe:/a:redhat:exploit_intelligence:0
collectionURL: https://access.redhat.com/downloads/content/package-browser/
packageName: exploit-intelligence-tech-preview/vulnerability-analysis-rhel9
- Red Hat · Red Hat Ansible Automation Platform 2
Source: CNA · 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Default status: unaffected
CPEs: cpe:/a:redhat:ansible_automation_platform:2
collectionURL: https://access.redhat.com/downloads/content/package-browser/
packageName: ansible-automation-platform-26/lightspeed-chatbot-rhel9
- Red Hat · Red Hat Ansible Automation Platform 2
Source: CNA · 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Default status: unaffected
CPEs: cpe:/a:redhat:ansible_automation_platform:2
collectionURL: https://access.redhat.com/downloads/content/package-browser/
packageName: ansible-automation-platform-27/lightspeed-chatbot-rhel9
- Red Hat · Red Hat OpenShift AI (RHOAI)
Source: CNA · 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Default status: unaffected
CPEs: cpe:/a:redhat:openshift_ai
collectionURL: https://access.redhat.com/downloads/content/package-browser/
packageName: rhoai/odh-mlflow-rhel9
- Red Hat · Red Hat OpenShift AI 2.25
Source: CNA · 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Default status: affected
1781826406 ≤ version < * — unaffected (rpm)
CPEs: cpe:/a:redhat:openshift_ai:2.25::el9
collectionURL: https://catalog.redhat.com/software/containers/
packageName: rhoai/odh-llama-stack-core-rhel9
- Red Hat · Red Hat OpenShift AI 3.3
Source: CNA · 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Default status: affected
1782310008 ≤ version < * — unaffected (rpm)
CPEs: cpe:/a:redhat:openshift_ai:3.3::el9
collectionURL: https://catalog.redhat.com/software/containers/
packageName: rhoai/odh-llama-stack-core-rhel9
- Red Hat · Red Hat OpenShift AI 3.4
Source: CNA · 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Default status: affected
1781622627 ≤ version < * — unaffected (rpm)
CPEs: cpe:/a:redhat:openshift_ai:3.4::el9
collectionURL: https://catalog.redhat.com/software/containers/
packageName: rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9
- BerriAI · litellm
Source: CNA · [email protected]
Default status: unknown
>= 1.74.2, < 1.83.7 — affected
Affected Products / Versions
- litellm / litellm
Source: NVD CPE · affected
Version / affected range: * · from (inclusive) 1.74.2 · before (exclusive) 1.83.7
cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:* - redhat / openshift_ai
Source: NVD CPE · affected
Version / affected range: * · from (inclusive) 2.25 · before (exclusive) 2.25.8
cpe:2.3:a:redhat:openshift_ai:*:*:*:*:*:*:*:* - redhat / openshift_ai
Source: NVD CPE · affected
Version / affected range: * · from (inclusive) 3.3 · before (exclusive) 3.3.4
cpe:2.3:a:redhat:openshift_ai:*:*:*:*:*:*:*:* - redhat / openshift_ai
Source: NVD CPE · affected
Version / affected range: 3.4
cpe:2.3:a:redhat:openshift_ai:3.4:*:*:*:*:*:*:*
References
- [email protected]
- [email protected]
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- CISA Advisory
Sources: NVD · FIRST EPSS · CISA KEV
Latest successful provider update; providers refresh independently.
Reported Context (14)
- These requests appear to attempt to exploit CVE-2026-42271 and CVE-2026-48710. Honeypots See Attempts to Exploit Starlette and LiteLLM Flaws
- CVE reference: CVE-2026-42271 Metasploit Update Adds Exploit Modules, Windows AArch64 Payloads and Enhancements
- In the sample Black Lotus Labs analyzed, the targeted LiteLLM endpoint (/mcp-rest/test/connection) is referenced in CVE-2026-42271, a command injection vulnerability in LiteLLM. PoeLLM Botnet Hides C2 Address in GitHub Poem, Infecting More Than 3,400 Servers
- Once a server is compromised, it becomes a springboard to spread the malware further, using scanning on ports 3000 and 4000, associated with Gotenberg and LiteLLM, and attempting to exploit CVE-2026-42271. PoeLLM Malware Targets Exposed AI Servers in Cryptomining Campaign
- They include a command injection flaw in LiteLLM (CVE-2026-42271) that leads to host takeover and API credential theft, and two Langflow flaws (CVE-2026-5027 and CVE-2025-3248) that let attackers write files to the host GTIG Finds Attackers Quickly Exploited an AI-Discovered BeyondTrust Flaw
CVE (86)
Malware (11)
People (10)
Threat Actors (5)
MITRE ATT&CK (18)
Vendors (34)
Products (96)
Tools (9)
Industries (6)
Countries (6)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
