BlackTreeCVE Intelligence
← Back to the CVE catalogue
Full vulnerability report · 2026
CVE-2026-42271High confidence

BerriAI LiteLLM Command Injection Vulnerability

BerriAI · litellm

Official source article: GitHub GHSA-V4P8-MG3P-G94G ↗. Check the applicable product and release in the original source.

8.7HighCVSS 4.0
Recommended action
Patch now

CISA confirms exploitation in the wild and lists 2026-06-22 as the remediation due date.

Patch available
R
Operational reassessment

Published severity in operational context

Open reassessment dashboard →
Published severityHighOperational priority:Critical, raised one band.upgradedsince 8 Jun 2026

Evidence used

  • CISA confirms exploitation in the wild.
  • EPSS is 91.44% for the current model date.

Compensating controls

  • Validate the affected product branch and deploy the verified fixed release.
  • Restrict the affected network interface to trusted sources where business-safe.
  • Increase monitoring for the attack path and post-exploitation behaviour described in the report.

Verification

  1. Confirm that the asset runs BerriAI litellm and falls inside the recorded affected range.
  2. Verify the installed build against the product-specific fixed version after deployment.
  3. Validate exposure, authentication requirements and compensating controls in the actual environment.
  4. Reopen this reassessment when CVSS, KEV, EPSS, exploit evidence or remediation changes.
Mitigation target: Within 3 daysRemediation target: Within 90 days

This automated reassessment organises public evidence. It does not know asset exposure, business impact or control effectiveness and does not replace CVSS or a human risk decision.

Open-source package ranges2 source-attributed ranges

These OSV and GitHub advisory ranges apply only to the named package and ecosystem. A listed fixed version is not a universal product patch or proof that an update is installed.

Ecosystem and packageAffected rangeFirst fixed versionEvidence
PyPIlitellmECOSYSTEM: introduced 1.74.2; fixed 1.83.71.83.7OSV record ↗aggregator derived · 10 Sep 2026
piplitellm>= 1.74.2, < 1.83.71.83.7GitHub advisory ↗upstream repository advisory · 9 Jun 2026
Direct vendor intelligence

Authoritative vendor CSAF and VEX advisories

Structured product status and remediation from the issuing vendor. Product-state explanations are always visible; large lists can be searched or downloaded.

2 current
CVE-2026-42271 · CSAF 2.0 · revision 3 · finalRed Hat Product Securitylitellm: LiteLLM: Authenticated command execution via MCP stdio test endpoints
8 fixed

The vendor explicitly identifies these products or versions as containing the fix.

  • registry.redhat.io/rhoai/odh-llama-stack-core-rhel9@sha256:59a4a3dc01e258bdd6aa463c8dbb34e14bd1a8357ef6ae3d4ea9e6c8ce062353_arm64 as a component of Red Hat OpenShift AI 2.25
  • registry.redhat.io/rhoai/odh-llama-stack-core-rhel9@sha256:66cc80e961fe991b063dc51467fa901dce3fb2afc383afed1c596ec432363022_amd64 as a component of Red Hat OpenShift AI 2.25
  • registry.redhat.io/rhoai/odh-llama-stack-core-rhel9@sha256:b6ec1fac474c9ff596322446656add0ebb10c449d623c37a3f71548957dc4c9c_amd64 as a component of Red Hat OpenShift AI 3.3
  • registry.redhat.io/rhoai/odh-llama-stack-core-rhel9@sha256:ee821288511aaf6e91080f8a925a425e5d26eeacc73f042b39469c65c2e7a139_arm64 as a component of Red Hat OpenShift AI 3.3
  • registry.redhat.io/rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9@sha256:1c962bba45e5cddaadd8ceff241417f9c3686aba1df8b6b511caf5a9901f2c40_amd64 as a component of Red Hat OpenShift AI 3.4
  • registry.redhat.io/rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9@sha256:1d6d4da4451688faa350b05558ed601e5c498b2382923f1bf45fc41958b098f6_s390x as a component of Red Hat OpenShift AI 3.4
  • registry.redhat.io/rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9@sha256:305bf281a63bff13b96466fb7adfd0962ac28e92d649ad692a86eb10db89a1a0_arm64 as a component of Red Hat OpenShift AI 3.4
  • registry.redhat.io/rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9@sha256:5149bc20e5d0a9e281ca3330d000d613b5987f46996e771067532af0fe3e0fb8_ppc64le as a component of Red Hat OpenShift AI 3.4
Summary
A flaw was found in LiteLLM, a proxy server (AI Gateway) for Large Language Model (LLM) APIs. Two endpoints, used for previewing an MCP server before saving it, accepted a full server configuration including command execution parameters. An authenticated user, even with low-privilege internal-user keys, could exploit this by sending a crafted configuration. This allows for arbitrary command execution on the proxy host with the privileges of the proxy process.
Remediation
For Red Hat OpenShift AI 2.25.8 see the following documentation, which will be updated shortly for this release, for important instructions on how to upgrade your cluster and fully apply this errata update: https://docs.redhat.com/en/documentation/red_hat_openshift_ai/
CVE-2026-42271 · CSAF 2.0 · revision 2 · finalStackable Product Security TeamStackable Security Advisory for: CVE-2026-42271
4 known not affected

The vendor explicitly states that these products are not affected by this CVE.

  • pkg:pypi/litellm@1.75.9@pkg:oci/airflow@sha256%3A413100ba2cb4db0d44057b3caf3bc8326ee40d9b3dd949ec289e5dc5f85ca7d9?arch=amd64&repository_url=oci.stackable.tech%2Fsdp%2Fairflow
  • pkg:pypi/litellm@1.80.12@pkg:oci/airflow@sha256%3A97d12e5a214c94ed8606cff7a859c79a8922120244e8dc899c8581a343615ff5?arch=amd64&repository_url=oci.stackable.tech%2Fsdp%2Fairflow
  • pkg:pypi/litellm@1.75.9@pkg:oci/airflow@sha256%3Ab76c7375a627636e13db6ac41147805172db85464e366e6fafd8c20e6a7e3046?arch=arm64&repository_url=oci.stackable.tech%2Fsdp%2Fairflow
  • pkg:pypi/litellm@1.80.12@pkg:oci/airflow@sha256%3Ae7949e338f28d85e51c70b1319a11ae545516dcf0eb75ca757fd69bf16e4590e?arch=arm64&repository_url=oci.stackable.tech%2Fsdp%2Fairflow
Summary
LiteLLM: Authenticated command execution via MCP stdio test endpoints
Remediation
No remediation text is recorded.
Optional official sources

National CERT insights
?CERT means Computer Emergency Response Team; CSIRT is the closely related term Computer Security Incident Response Team.

Choose official national sources for this report. Each advisory shows its original language. Your selection is remembered on this device and included in shared links.

Official European source

ENISA European Vulnerability Database

Official EUVD identifiers, advisory evidence and known-exploited context. Missing fields are not treated as evidence of low risk.

1 current
ENISA EUVD identifier

EUVD-2026-28507

CISA KEV mirrored by ENISA

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.

EUVD state
Present in the current official mapping
Known exploitation
Recorded by ENISA since 8 Jun 2026. Evidence sources: cisa_kev.
ENISA score
8.7 · CVSS 4.0
Advisory evidence
4 linked advisory records
Explicit mitigation evidence

Only statements that explicitly mention a fix, patch, update, workaround or mitigation are shown here.

  • csaf_ncscnl · NCSC-2026-0137Kwetsbaarheden verholpen in LiteLLM door BerriAI
Recommended actionPatch now

CISA confirms exploitation in the wild and lists 2026-06-22 as the remediation due date.

Patch available
01

What, why and how

BerriAI LiteLLM contains a command injection vulnerability that could allow any authenticated user, including holders of low-privilege internal-user keys, to run arbitrary commands on the host.

What

BerriAI LiteLLM contains a command injection vulnerability that could allow any authenticated user, including holders of low-privilege internal-user keys, to run arbitrary commands on the host.

Why

Untrusted input reaches a command interpreter without sufficient validation or separation from command syntax.

How

An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.

What

BerriAI LiteLLM contains a command injection vulnerability that could allow any authenticated user, including holders of low-privilege internal-user keys, to run arbitrary commands on the host.

Why

Untrusted input reaches a command interpreter without sufficient validation or separation from command syntax.

How

An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.

02

Exploit reality and attack path

CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.

Observed exploitation
?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.
Confirmed in the wild

CISA added this CVE to its Known Exploited Vulnerabilities catalogue on 2026-06-08.

Public PoC / exploit material
?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.
None recorded

No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.

Likely attack path
a network path → Improper Neutralization of Special Elements used in a Command ('Command Injection') → cause the confidentiality, integrity or availability impact described by the vendor
Attack surface
Network
Privileges required
Low: a basic authenticated account is required
User interaction
None
Attack complexity
Low: no specialised conditions are recorded
Security boundary
Not a CVSS 4.0 base metric
Weakness
?CWE means Common Weakness Enumeration: a standard category for the underlying weakness.
CWE-77 ↗

CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection'). The product constructs all or part of a command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended command when it is sent to a downstream component.

CVSS vector
?CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity.
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

Common Vulnerability Scoring System 4.0: the compact vector below is decoded into plain language.

AVNetworkAttack vector: The vulnerable component can be reached over a network.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.ATPresentAttack requirements: A particular deployment or execution condition must be present.PRLowPrivileges required: The attacker needs basic user-level privileges.UINoneUser interaction: No action by another user is required.VCHighVulnerable-system confidentiality: A successful attack can cause a major loss.VIHighVulnerable-system integrity: A successful attack can cause a major loss.VAHighVulnerable-system availability: A successful attack can cause a major loss.SCHighSubsequent-system confidentiality: A successful attack can cause a major loss.SINoneSubsequent-system integrity: No direct loss is represented by this metric.SANoneSubsequent-system availability: No direct loss is represented by this metric.
Post-exploitation / living off the land
No specific living-off-the-land technique is confirmed in the structured sources. Monitor normal administration tools for activity inconsistent with the affected service's baseline.
NetworkCWE-77CISA KEV
A

Official authority intelligence

Only matched European and national findings are included. Language selectors and unavailable sources are omitted.

ENISA EUVD · EUVD-2026-28507Known-exploited evidence recorded

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.

Official EUVD record ↗
BSI · German · WID-SEC-2026-1288LiteLLM: Mehrere Schwachstellen

Ein Angreifer kann mehrere Schwachstellen in LiteLLM ausnutzen, um einen SQL-Injection-Angriff durchzuführen und sich unbefugten Zugriff zu verschaffen oder um beliebigen Programmcode mit den Rechten des Dienstes auszuführen

Official advisory ↗
JVN iPedia · Japanese · JVNDB-2026-015002LiteLLMにおける複数の脆弱性

LiteLLMはOpenAI（またはネイティブ）形式のLLM APIを呼び出すためのプロキシサーバー（AIゲートウェイ）です。バージョン1.74.2から1.83.7未満の間、MCPサーバーを保存前にプレビューするために使用される2つのエンドポイント — POST /mcp-rest/test/connection および POST /mcp-rest/test/tools/list — は、stdioトランスポートで使用されるcommand、args、およびenvフィールドを含む完全なサーバー構成をリクエストボディで受け入れていました。stdio構成で呼び出された場合、これらのエンドポイントは接続を試み、指定されたコマンドをプロキシホスト上でプロキシプロセスの権限でサブプロセスとして起動しました。これらのエンドポイントは有効なプロキシAPIキーによってのみアクセスが制御されており、役割チェックがありませんでした。そのため、低権限の内部ユーザーキー所有者を含む認証済みユーザーは任意のコマンドをホスト上で実行できました。この問題はバージョン1.83.7で修正されました。

Official advisory ↗
KISA KrCERT/CC · Korean · KNVD-6941美 CISA 발표 주요 Exploit 정보공유(Update. 2026-09-02)

Kludex Starlette HTTP Request/Response Smuggling Vulnerability

Official advisory ↗
KISA KrCERT/CC · Korean · KNVD-6835美 CISA 발표 주요 Exploit 정보공유(Update. 2026-06-08)

BerriAI LiteLLM Command Injection Vulnerability

Official advisory ↗
NCSC-NL · Dutch · NCSC-2026-0137Kwetsbaarheden verholpen in LiteLLM door BerriAI

LiteLLM versions 1.74.2 to before 1.83.7 had two preview endpoints allowing authenticated users with a proxy API key to execute arbitrary commands on the host, fixed by requiring the PROXY_ADMIN role in version 1.83.7.

Official advisory ↗
03

Patch and workaround

Operational remediation based on structured source evidence.

Status
?Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change.
Patch available
Affected
LiteLLM: 1.74.2, < 1.83.7
Fixed
Action
For Red Hat OpenShift AI 2.25.8 see the following documentation, which will be updated shortly for this release, for important instructions on how to upgrade your cluster and fully apply this errata update: https://docs.redhat.com/en/documentation/red_hat_openshift_ai/
Workaround
A mitigation or workaround reference is available from the source linked below; validate it against the affected product and version.
04

Evidence and provenance

Published 8 May 2026 · Last source change 15 Jul 2026, 00:57 UTC · CWE-77 · Improper Neutralization of Special Elements used in a Command ('Command Injection')

CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source
?The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.
FIRST · tracked since 2026-08-14
European sourceENISA EUVD · EUVD-2026-28507
Product sourceCNA
Remediation sourceVendor CSAF · Red Hat Product Security
CWE sourceCNA
NVD statusNVD enriched

Core structured fields are present and their contributing authorities are shown above.

Material change intelligence

What changed after publication

View recent updates ↗
  1. BlackTree coverageBlackTree article coverage changed from 1 BlackTree article to 2 BlackTree articles.
    Before
    1 BlackTree article
    After
    2 BlackTree articles
    BlackTree editorial ↗
  2. BlackTree coverageBlackTree article coverage changed from no BlackTree article to 1 BlackTree article.
    Before
    no BlackTree article
    After
    1 BlackTree article
    BlackTree editorial ↗
  3. Affected versionsThe structured affected or fixed version information changed.
    Before
    >= 1.74.2, < 1.83.7 · Fixed: An authoritative update reference is available, but the fixed version is not recorded in the structured CVE fields. Check the linked vendor advisory for the applicable release.
    After
    litellm: >= 1.74.2, < 1.83.7 · Fixed: RHSA-2026:28960: Red Hat OpenShift AI 2.25
    CNA ↗
Material fields only · duplicate refreshes suppressed · history retained for the configured operational retention period
CVE published
Added to CISA KEV
Fixed release or patch reference recorded
ENISA EUVD · EUVD-2026-28507↗Vendor CSAF · Red Hat Product Security↗CISA KEV record↗CVE authority or vendor reference · GitHub GHSA-V4P8-MG3P-G94G↗Official CVE record (CNA and ADP data)↗NVD record↗
Technical terms and abbreviations used in this report
CVE
Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
CVSS
Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
EPSS
Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
CWE
Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
CNA
CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
CISA ADP
Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
NVD
National Vulnerability Database: NIST's enrichment service for CVE records.
CERT / CSIRT
A computer security incident response team that publishes warnings or coordinates incident response.
PoC
Proof of concept: public material that demonstrates or helps reproduce exploitation.
CSAF
Common Security Advisory Framework: a machine-readable format for security advisories.
LoTL
Living off the land: abuse of legitimate tools or system functions during an attack.
Free version - for non-commercial use only.CVE-2026-42271 · cve.blacktree.nl