LiveActive security incident?Get immediate response
CVE Record

CVE-2026-42271: LiteLLM: Authenticated command execution via MCP stdio test endpoints

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.

HighCVSS 8.8Known exploitedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysishigh

Security readout for executives and security teams

Plain-English summary

LiteLLM versions 1.74.2 through before 1.83.7 let any authenticated proxy API key holder run commands on the server through MCP preview test endpoints. A low-privilege internal key could become full host compromise. CISA KEV indicates known exploitation, so this should be treated as urgent where LiteLLM is deployed.

Executive priority

Prioritize immediate remediation for any internet-facing or broadly accessible LiteLLM proxy. KEV status and host command execution make this a business-impact risk, especially where LiteLLM can reach secrets, model credentials, internal systems, or production data.

Technical view

The MCP REST test endpoints accepted attacker-supplied stdio server configuration, including command, args, and env. When testing the connection or tool list, LiteLLM spawned the supplied command as a subprocess under the proxy process privileges. The flaw required a valid proxy API key but no elevated role. Patch: version 1.83.7.

Likely exposure

Organizations running LiteLLM proxy versions >=1.74.2 and <1.83.7 are exposed if users or services can call /mcp-rest/test/connection or /mcp-rest/test/tools/list with a valid proxy API key.

Exploitation context

CISA KEV listing supports known exploitation. The sources do not provide exploit volume, targeting details, public proof-of-concept status, or indicators of compromise. Exploitation is authenticated, but the advisory states low-privilege internal-user keys were sufficient.

Researcher notes

Key research focus is authorization failure around MCP stdio preview behavior. Confirm version range, endpoint reachability, authentication paths, and process execution telemetry. Do not assume unauthenticated exposure; the cited advisory describes authenticated exploitation with any valid proxy API key.

Mitigation direction

  • Upgrade LiteLLM to version 1.83.7 or later.
  • Restrict access to LiteLLM proxy endpoints to trusted networks and users.
  • Rotate or revoke unnecessary LiteLLM proxy API keys.
  • Review vendor and Red Hat advisories for environment-specific remediation.
  • Monitor for unexpected child processes from the LiteLLM proxy process.

Validation and detection

  • Inventory LiteLLM deployments and confirm installed versions.
  • Identify whether affected MCP REST test endpoints are reachable.
  • Review proxy API key issuance, ownership, and privilege levels.
  • Check application, audit, and EDR logs for calls to affected endpoints.
  • Look for unexpected subprocesses spawned by LiteLLM during the exposure window.
Prepared
Confidence
high
Sources
7

Public sources used

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · medium confidence lookup

CWE-77: Command execution behavior lookup

Command injection weaknesses can lead defenders to review execution techniques and command interpreter telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
cwe · medium confidence lookup

CWE-78: Command execution behavior lookup

Command injection weaknesses can lead defenders to review execution techniques and command interpreter telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-42271 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
High
CVSS
8.8 (3.1)
Known Exploited
Yes
Published

Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

2CVSS vectors
7Timeline events
2ADP providers
10Source links

CISA KEV status

Status
Known exploited
Source
CISA-ADP
Date added
KEV reference

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: activeAutomatable: noTechnical Impact: total

CVSS vector scores

2 official scores

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
8.8CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H2.85.9redhat-SADP
8.7CVSS 4.0HighCVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:N/SA:N——GitHub_M

Vulnerability scoring details

Base CVSS 4.0 score

8.7High
CVSS 4.0 vector shape for CVE-2026-42271Attack VectorAttack ComplexityAttack RequirementsPrivileges RequiredUser InteractionVS ConfidentialityVS IntegrityVS AvailabilitySS ConfidentialitySS IntegritySS Availability

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

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Attack Requirements
NonePresent
Privileges Required
NoneLowHigh
User Interaction
NonePassiveActive
VS Confidentiality
HighLowNone
VS Integrity
HighLowNone
VS Availability
HighLowNone
SS Confidentiality
HighLowNone
SS Integrity
HighLowNone
SS Availability
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. ADP timelineredhat-SADP

    Made public.

  3. CVE publishedCVE Program

    The CVE record was published.

  4. ADP timelineredhat-SADP

    Reported to Red Hat.

  5. Added to KEVCISA-ADP

    CISA Known Exploited Vulnerabilities metadata lists this CVE as known exploited.

  6. ADP timelineCISA-ADP

    CVE-2026-42271 added to CISA KEV

  7. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvcother:kev
  • 2026-06-08T00:00:00.000Z: CVE-2026-42271 added to CISA KEV
redhat-SADPlitellm: LiteLLM: Authenticated command execution via MCP stdio test endpoints
other:Red Hat severity ratingcvssV3_1
  • 2026-05-08T04:02:12.169Z: Reported to Red Hat.
  • 2026-05-08T03:35:16.758Z: Made public.

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
BerriAIlitellm>= 1.74.2, < 1.83.7Listed
Weakness

CWE details

CWE-77CWE-78

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.