Skip to main content
veriom
Menu

Explore Veriom products, resources, and account pages.

CVE-2026-42271BerriAI LiteLLM Command Injection Vulnerability

Patch nowHigh8.7Exploited, CISA due date 2026-06-22EPSS 91%, higher than 100% of scored CVEs

CVE-2026-42271 is a command injection in BerriAI LiteLLM, rated high (8.7 on CVSS 4.0).

Why this priority: Exploited in the wild: listed in CISA's KEV catalog.

Published · Updated · NVD status: Analyzed

What it is

Input ends up inside a command the software runs, so an attacker can add commands of their own. Input reaches an operating-system command line, letting an attacker run their own commands on the host.

How it is reached

An attacker can exploit it over the network, with an ordinary user account, and nobody has to click anything. Success also depends on conditions the attacker does not fully control.

What an attacker gains

A successful attack can read the data it protects, change data or behaviour and take it offline. In practice, this kind of flaw lets an attacker run commands or code with the privileges of the affected service. The damage can spread past the vulnerable component into others.

Is it being exploited?

CISA added it to the Known Exploited Vulnerabilities catalog on 2026-06-08: it is being exploited in the wild. EPSS estimates a 91% chance of exploitation activity in the next 30 days, higher than 100% of scored CVEs.

What to do

  1. Treat it as urgent: it is on CISA's KEV list. CISA's deadline for US federal agencies: 2026-06-22.
  2. Upgrade BerriAI LiteLLM to 1.83.7 or later. The patch notes are linked below.
  3. Until it is patched, review who holds accounts that can reach it.
  4. Check exposed instances for signs of compromise, not only for the version.

Description from NVD

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.

What this means for your architecture.

A CVE names a product. Whether it matters depends on where that product sits in your systems: what reaches it, which trust boundary it guards and what it can reach once compromised. Veriom maps your components, their relationships and your trust boundaries from your code, cloud and delivery evidence, so you can see where a component like this sits. The radar itself does not look at your systems.

Components it touches

  • Application servers and the hosts they run on. The flaw sits between untrusted input and code or command execution.
  • Template engines. The flaw sits between untrusted input and code or command execution.

Trust boundaries in play

  • Authenticated network access. An account is needed, so exposure follows who can sign in: customers, partners or staff.
  • Isolation between components. The impact crosses out of the vulnerable component into others it should be isolated from.
  • Between untrusted input and code or command execution. An attacker who crosses it can run commands or code with the privileges of the affected service.

Questions to answer about your own systems

  • Where does BerriAI LiteLLM run in your systems, and at which version?
  • Which of those instances can be reached from the internet or partner networks?
  • What can it reach once compromised: which data stores, secrets and services?
See how Veriom maps an architectureTake the interactive tour

Read more

Sources

  • CVE records and CVSS scores from the NVD CVE API. This product uses the NVD API but is not endorsed or certified by the NVD.
  • Exploitation status from CISA’s Known Exploited Vulnerabilities catalog.
  • Exploit likelihood from FIRST’s Exploit Prediction Scoring System (EPSS), refreshed daily.
  • Explanations are written by Veriom from fixed templates over each record’s data, not by a person reviewing each CVE. Descriptions are quoted from the records as published.