FalehSec Exploited-vulnerability triage · joined from CISA KEV, NVD CVSS and EPSS

CVE-2026-42271

BerriAI · LiteLLM · BerriAI LiteLLM Command Injection Vulnerability

Verdict
Patch soon · actively exploited, not reachable unauthenticated from the internet, and in the top 5% of CVEs by near-term exploitation probability

Added to CISA KEV 2026-06-08 · exploited in the wild for 111 days

What an attacker can reach How likely Time What CISA says to do Sources All 545

What an attacker can reach

CVSS 8.7 HIGH. The score is a summary; these three components are the part that decides whether something scanning the internet can use it.

Attack vectornetworkreachable over the network, with no local access needed
Privileges requiredlowneeds some credentials, so a fully anonymous attacker cannot reach it directly
User interactionnonecan be triggered with nobody interacting with the page or request
Base vectorCVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
WeaknessCWE-77

This describes the vulnerability. It says nothing about whether your systems run it.

How likely

EPSS puts the probability of exploitation in the next 30 days at 0.1275, which places it in the top 5% of all tracked CVEs. The percentile is the more useful half: 0.18 in absolute terms sounds low until you know most of the internet-facing software in the world scores under that.

EPSS probability0.1275
Percentile0.961 — top 5%

Time

Added to KEV2026-06-08
Days exploited111
Federal remediation duenot set
Ransomware useno known ransomware campaign use

What CISA says to do

Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.

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.

Sources