Vulnerability report

Exploited in the wild Confirmed confidence In CISA KEV

CVE-2026-42271

litellm Authenticated command execution

BerriAI / litellm · affected before *

Watch CVE-2026-42271 Browse KEV feed
Severity
CVSS 8.7 · High
Confidence
Confirmed
Exploit status
Exploited in the wild
EPSS
92.6%
First observed
—
Last observed
—

Decision summary

What security teams need to know first

Direct answers before the deeper technical record.

What it is

CVE-2026-42271 is a vulnerability affecting BerriAI litellm. 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...

Is it exploited?

Yes. Previdian tracks this CVE as a known exploited vulnerability. Confidence is confirmed. Listed in CISA KEV. Also confirmed by third-party sources.

Who is affected?

BerriAI / litellm affected before *.

What should we do?

Prioritize remediation. Validate affected assets and apply vendor fixes on an accelerated timeline.

Overview

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format

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.

Red Hat Unaffected
Red Hat OpenShift AI 2.25 rhoai/odh-llama-stack-core-rhel9
Before *
Red Hat Unaffected
Red Hat OpenShift AI 3.3 rhoai/odh-llama-stack-core-rhel9
Before *
Red Hat Unaffected
Before *
Red Hat Unaffected
All versions (default: unaffected)
Red Hat Unaffected
Red Hat Ansible Automation Platform 2 ansible-automation-platform-26/lightspeed-chatbot-rhel9
All versions (default: unaffected)
Red Hat Unaffected
Red Hat Ansible Automation Platform 2 ansible-automation-platform-27/lightspeed-chatbot-rhel9
All versions (default: unaffected)
Red Hat Unaffected
Red Hat OpenShift AI (RHOAI) rhoai/odh-mlflow-rhel9
All versions (default: unaffected)
BerriAI Affected
litellm
>= 1.74.2, < 1.83.7
Published
08 May 2026
Exploitation Reported
08 Jun 2026
Attack vector
Remote
Complexity
Low
Privileges
Low
User interaction
None

Tags

cisa nuclei_scanner

CVE References

Exploitation evidence

Why Previdian marks this CVE as exploited

Third-party attestation and first-party sensor observation are shown separately so teams can judge the evidence chain.

Exploited in the wild

CISA

Recorded 08 Jun 2026

A trusted third party reported exploitation.

Proof of concept available

GitHub

Recorded 09 Jun 2026

Public scanner or PoC coverage increases practical exploitability.

Known exploited vulnerability sources

Per-source evidence links for KEV attestations are available through the Previdian Pro API.

Learn about Pro API access
Source Added
CISA First 2026-06-08 18:00 UTC
CVE 2026-06-08 18:10 UTC
All CISA Advisories 2026-06-08 20:20 UTC
The Hacker News 2026-06-09 07:20 UTC
The Shadowserver 2026-07-07 10:15 UTC
Google Threat Intelligence 2026-09-30 15:21 UTC

Detection

Operational artifacts and observed signals

Make the evidence actionable in scanner, SOC, and edge-control workflows.

Observed signals

Request targets
User-Agents
Callback hosts
0
0
0

Request targets and User-Agents available in Pro. Callback host details available in Enterprise.

Virtual patch status

No Previdian virtual patch is currently available. Future rules ship for ModSecurity, Cloudflare, and AWS WAF.

Learn about virtual patches →

Scanner Artifacts

Scanner and exploit-framework references linked to this CVE.

Scanner Reference Detected
Nuclei https://github.com/projectdiscovery/nuclei-templates/blob/main/http/cves/2026/CVE-2026-42271.yaml 03 Jun 2026

Risk and context

Severity, weaknesses, and research context

CVSS v4.0

8.7 High

Potential damage if exploited. Separate from whether attackers are using it.

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

EPSS

92.6%

Estimated chance of exploitation in the next 30 days. Previdian's warning comes from evidence, not this score.

Weaknesses

Improper Neutralization of Special Elements used in a Command ('Command Injection') CWE-77 Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') CWE-78

Recent mention · Rapid7

Metasploit Wrap Up: A Collection of What Can Only Be Called Eclectic Modules

Read full advisory

All CVSS Scores

CVSS v4.0 8.7 High

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

CVSS v3.1 8.8 High

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

All Mentions

Recent mention · Rapid7

Metasploit Wrap Up: A Collection of What Can Only Be Called Eclectic Modules

Rapid7 · 09 Oct 2026

Recent mention · Google Threat Intelligence

Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability...

Google Threat Intelligence · 30 Sep 2026

Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact of artificial intelligence (AI) on the vulnerability threat landscape. We found that AI is measurably changing not just the pace of vulnerability discovery and exploitation, but also the types and typical risk profiles of vulnerabilities that are being discovered. Key findings:  Vulnerability disclosures doubled: the number of vulnerabilities disclosed per month doubled, rising from 5,045...

Recent mention · The Hacker News

LiteLLM Flaw CVE-2026-42271 Exploited in the Wild, Chains to Unauthenticated RCE

The Hacker News · 09 Jun 2026

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Monday added a high-severity flaw impacting BerriAI LiteLLM to its Known Exploited Vulnerabilities (KEV) catalog, citing evidence of active exploitation. The vulnerability, tracked as CVE-2026-42271 (CVSS score: 8.7), is a command injection vulnerability that could allow any authenticated user to run arbitrary commands on the

Recent mention · All CISA Advisories

CISA Adds Two Known Exploited Vulnerabilities to Catalog

All CISA Advisories · 08 Jun 2026

CISA has added two new vulnerabilities to its Known Exploited Vulnerabilities (KEV) Catalog, based on evidence of active exploitation. CVE-2026-42271 BerriAI LiteLLM Command Injection Vulnerability CVE-2026-50751 Check Point Security Gateway Improper Authentication Vulnerability These types of vulnerabilities are a frequent attack vector for malicious cyber actors and pose significant risks to the federal enterprise. Binding Operational Directive (BOD) 22-01: Reducing the Significant Risk of Known Exploited Vulnerabilities established the KEV Catalog as a living list of known Common...

Potential Proof of Concepts

These PoCs are unverified and could contain malware. Use at your own risk.

BerriAI LiteLLM SQL injection

pruva · Created 2026-07-07 08:05:39 UTC

Severity: HIGH | CVE: CVE-2026-42271 | Package: BerriAI LiteLLM

LiteLLM - Command Injection

nuclei · Created Unknown

Timeline

From disclosure to observed exploitation

  1. 15:21 UTC

    KEV confirmed by Google Threat Intelligence

    Exploitation attested by an external source

  2. 10:15 UTC

    KEV confirmed by The Shadowserver

    Exploitation attested by an external source

  3. 14:21 UTC

    Public PoC available

    Public proof-of-concept code published

  4. 07:20 UTC

    KEV confirmed by The Hacker News

    Exploitation attested by an external source

  5. 20:20 UTC

    KEV confirmed by All CISA Advisories

    Exploitation attested by an external source

  6. 18:10 UTC

    KEV confirmed by CVE

    Exploitation attested by an external source

  7. 18:00 UTC

    Added to CISA KEV

    Listed in the CISA Known Exploited Vulnerabilities catalog

  8. 04:30 UTC

    Nuclei template available

    Scanner coverage available

  9. 03:35 UTC

    CVE published

    Vulnerability disclosed publicly

  10. 11:53 UTC

    CVE ID reserved

    Identifier reserved by the CNA

Pro API

Automate this intelligence

Confidence, exploit status, sensor telemetry, PoCs, scanner integrations, mentions, and tags are available programmatically for VM, SOC, and CTI workflows.

Start 14-day Pro trial Read API docs
  • Evidence confidence and provenance
  • First-party sensor telemetry
  • PoC and scanner references
  • Affected versions and enrichment
  • Automation-ready JSON delivery

GET /api/v2/pro/kevs/CVE-2026-42271

Free JSON includes basic KEV fields 
{
  "cve_id": "CVE-2026-42271",
  "confidence": "Confirmed",
  "cvss_score": 8.7,
  "cvss_estimated": false,
  "epss_score": 0.9257,
  "exploit_status": {
    "exploited_in_the_wild": true,
    "active_exploitation_observed": false
  },
  "sensor_telemetry": { "attempts": 0, "sensors": 0 }
}