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

CVE-2026-42208

BerriAI · LiteLLM · BerriAI LiteLLM SQL Injection Vulnerability

Verdict
Patch first · actively exploited, reachable from the internet without credentials, and in the top 10% of CVEs by near-term exploitation probability

Added to CISA KEV 2026-05-08 · exploited in the wild for 142 days

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

What an attacker can reach

CVSS 9.3 CRITICAL. 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 requirednoneneeds no credentials at all
User interactionnonecan be triggered with nobody interacting with the page or request
Base vectorCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/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-89

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 0.0577, which places it in the top 10% 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 probability0.0577
Percentile0.928 — top 10%

Time

Added to KEV2026-05-08
Days exploited142
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 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.

Sources