CVE-2026-42271 litellm · litellm

BerriAI LiteLLM Proxy MCP Test Endpoint Command Execution

Vulnerability at a glance

Severity, exploitation likelihood & attack requirements

CVSS v4.0 severity
8.7High
EPSS · exploitation likelihood
92.57% Probability within 30 daysPercentile 99.8
EPSS trend
Up 8.976 pp Since 2026-09-22 · percentage points
Known exploitation
Known exploited CISA KEV catalog
Attack vector
NetworkRemotely reachable
Attack complexity
LowFewer obstacles to exploitation
Privileges required
LowBasic privileges required
User interaction
NoneNo user action needed
Exploit availability & maturity
Not scored Availability not established No explicit exploit maturity assessment View exploit evidence
How to read the colors & trend
Higher exposureElevatedModerateLower exposureUnknown / unassessed

CVSS colors follow its reported severity. Attack-factor colors describe each requirement, not an overall risk rating. Gray also covers absence from KEV; absence does not establish safety.

EPSS display bands: below 1% blue, 1–10% amber, 10–50% orange, 50% and above red. These are presentation bands, not FIRST severity categories. The trend compares daily EPSS probabilities, not percentile ranks; “pp” means percentage points. The sparkline shows relative movement, with its vertical scale fitted to the observed scores.

Already protected by existing Atomicorp rules No new CVE-specific rule required.

Atomicorp ModSecurity protection

Protected by Atomicorp rules

Atomicorp ModSecurity rules block attacks exploiting this vulnerability when blocking is enabled. Keep your rules current.

By targeting underlying attack techniques and CWE weakness classes, existing rules can protect against newly disclosed vulnerabilities. Rule changes are regression-tested against attack and false-positive corpora.

2 rules identified Verified 2026-09-29 View rules & research details →

WAF protection applies to the tested attack paths; it does not change the CVSS or EPSS score. Keep your software patched and your Atomicorp rules current.

CISA SSVC assessment

CISA ADP · Assessed 2026-06-08 · SSVC 2.0.3

Exploitation
Active exploitation
Automatable
No
Technical Impact
Total

Stakeholder-Specific Vulnerability Categorization records CISA’s assessment of exploitation, automation, and technical impact. “None reported” reflects the assessment date; it does not establish that no exploit exists. View SSVC source details.

On this page

CVE Details

Technical vulnerability details · CVSS assessments, exploit evidence & CPE data

CVSS assessments

CVSS v4.0 · security-advisories@github.com

  • Base score: 8.7
  • Base severity: HIGH
  • Assessment type: Secondary
  • Source identifier: security-advisories@github.com
  • Full 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
    • Attack vector: Network
    • Attack complexity: Low
    • Attack requirements: Present
    • Privileges required: Low
    • User interaction: None
    • Vulnerable-system confidentiality: High
    • Vulnerable-system integrity: High
    • Vulnerable-system availability: High
    • Subsequent-system confidentiality: High
    • Subsequent-system integrity: None
    • Subsequent-system availability: None
    • Safety: Not defined
  • Exploit maturity: Not scored

CVSS v3.1 · NVD

  • Base score: 8.8
  • Base severity: HIGH
  • Exploitability subscore: 2.8
  • Impact subscore: 5.9
  • Assessment type: Primary
  • Source identifier: nvd@nist.gov
  • Full vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
    • Attack vector: Network
    • Attack complexity: Low
    • Privileges required: Low
    • User interaction: None
    • Scope: Unchanged
    • Confidentiality impact: High
    • Integrity impact: High
    • Availability impact: High
  • Exploit maturity: Not scored

CVSS v3.1 · Unresolved assessment provider

  • Base score: 8.8
  • Base severity: HIGH
  • Exploitability subscore: 2.8
  • Impact subscore: 5.9
  • Assessment type: Secondary
  • Source identifier: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  • Full vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
    • Attack vector: Network
    • Attack complexity: Low
    • Privileges required: Low
    • User interaction: None
    • Scope: Unchanged
    • Confidentiality impact: High
    • Integrity impact: High
    • Availability impact: High
  • Exploit maturity: Not scored

Exploitability and impact subscores describe the vulnerability’s technical characteristics. Exploit maturity describes the reported state of exploitation; these are separate measures.

Assessment source: NVD record · CVE record

CISA SSVC assessments

These are CISA’s published decision points at the assessment time. They are not a complete organization-specific prioritization decision.

  • Provider: CISA ADP
  • Provider identifier: 134c704f-9b21-4f2e-91b3-4a467353bcc0
  • SSVC version: 2.0.3
  • Role: CISA Coordinator
  • Assessment timestamp: 2026-06-08T17:47:03.864516Z
  • Exploitation: active
  • Automatable: no
  • Technical Impact: total
  • Source: CISA ADP in the CVE record

Vulnerable CPE configurations

  • cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*
    • Version start (inclusive): 1.74.2
    • Version end (exclusive): 1.83.7
    • NVD match criteria ID: D249DFDB-5D0D-4053-A997-0900F77F9A13
  • cpe:2.3:a:redhat:openshift_ai:*:*:*:*:*:*:*:*
    • Version start (inclusive): 2.25
    • Version end (exclusive): 2.25.8
    • NVD match criteria ID: 2823BDAD-B884-4664-93D8-A99DDE5B230E
  • cpe:2.3:a:redhat:openshift_ai:*:*:*:*:*:*:*:*
    • Version start (inclusive): 3.3
    • Version end (exclusive): 3.3.4
    • NVD match criteria ID: 0653F079-4206-402F-AF7E-C1A6B0C7D32B
  • cpe:2.3:a:redhat:openshift_ai:3.4:*:*:*:*:*:*:*
    • NVD match criteria ID: 138068CA-95F4-496B-8056-94E24190B17F

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.

  1. Maintain the observed Atomicorp protections. Keep your Atomicorp commercial rules current and confirm that the selected observed rules (330791 , 340152 ) have not been locally disabled. Atomicorp commercial rules are enabled by default. If you use Atomic WAF, review the applicable policy and rule settings.

  2. Apply the vendor’s remediation. WAF protection is defense in depth and does not replace upgrading or following the affected vendor’s guidance.

    • Affected versions: BerriAI litellm version >= 1.74.2, < 1.83.7.
    • The CVE record does not include written upgrade or workaround instructions, but it does publish the following patch or mitigation reference:
    • CISA KEV 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.
    • CISA KEV federal remediation due date: 2026-06-22

  3. Validate after changes. Confirm rule updates are current, review WAF events for the affected application, and test application behavior after vendor upgrades, mitigations, or local policy changes.

Research Notes

Atomicorp WAF protections are designed around attack techniques and exploit behaviors, allowing existing protections to apply across multiple vulnerabilities without requiring a unique rule for every CVE.

Public Vulnerability References

Test or Research Source

Research Note Context

This research note documents exploit-technique analysis associated with this vulnerability and references Atomicorp WAF protections observed during engineering review, testing, or validation activities.

Atomicorp security controls are generally designed to identify and mitigate attack techniques and exploit behaviors rather than individual CVE identifiers. As a result, protections developed for one vulnerability may also apply to related attack variants and future vulnerabilities using similar techniques.

Learn More

Atomicorp develops commercially supported security technologies for web applications, servers, endpoints, workloads, and legacy enterprise platforms.

Organizations interested in protecting systems against exploit techniques associated with vulnerabilities such as this one can learn more about:

  • Atomic ModSecurity Rules: commercially maintained WAF rules for ModSecurity deployments, including protections for web attacks, bots, scanners, malware, exploitation attempts, and emerging vulnerability classes.
  • Atomic WAF: an enterprise web application firewall with Atomicorp rules, centralized management, reporting, authentication controls, and operational tooling.
  • Atomic ModSecurity Integrator: a special licensing option for MSPs, MSSPs, OEMs, VARs, reverse proxy providers, and other integrators who want to incorporate Atomicorp ModSecurity rule technology into their own products or services.
  • Atomic OSSEC: an enterprise OSSEC-based intrusion detection, compliance, and security monitoring platform.
  • Atomic Protector: workload protection for Linux, web, cloud, data center, and hybrid environments.

For additional information, product evaluations, or technical discussions, visit https://www.atomicorp.com/ or https://modsecurity.io/ .