Patchfirst
CVE-2026-42208 KEVPublic exploit Critical · 9.8 EPSS 89.4%

BerriAI LiteLLM SQL Injection Vulnerability

BerriAI · LiteLLM

Summary

A SQL injection flaw in BerriAI's LiteLLM proxy server (AI Gateway) arises because the API key validation query used during proxy authentication checks concatenates the caller-supplied key into the SQL text rather than passing it as a bound parameter. An unauthenticated remote attacker can exploit this by sending a crafted Authorization header to any LLM API route, such as POST /chat/completions, reaching the query through the error-handling path, which can expose or modify data in the proxy's database and the credentials it manages.

Official description · NVD

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.

Breakdown
74.8 / 100
Exploited
Yes, in CISA KEV
Reports
0
Tactics
3/15

How an attack unfolds

Based on mappings. Select a step to see the evidence.
  1. How attackers get in

  2. What they do

First seen exploited 11 days before it was disclosed. Public exploit code (Metasploit) was available 18 days before disclosure.

  1. Public exploit codeMetasploit18 days before
  2. First seen exploitedVulnCheck KEV evidence11 days before
  3. DisclosedAdded to CISA KEVEU database agreesday 0

CISA KEV listing is when exploitation was confirmed, not necessarily the first attack.

techniques

3 , grouped by in kill-chain order, 3 cited passages 3

Initial AccessTA0001

Exploit Public-Facing Application T1190 Medium
AI mapping from the description · how it is exploited

Unauthenticated crafted HTTP request to public-facing app

An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route
From the official description (NVD) Original (opens in a new tab) ↗

CollectionTA0009

Data from Local System T1005 Medium
AI mapping from the description · primary impact

Attacker reads data from proxy database

An attacker could read data from the proxy's database
From the official description (NVD) Original (opens in a new tab) ↗

ImpactTA0040

Stored Data Manipulation T1565.001 Medium
AI mapping from the description · primary impact

Database modification via injected query

may be able to modify it
From the official description (NVD) Original (opens in a new tab) ↗

Detection

0 rules for this CVE · 169 general rules for its techniques

Rules for this CVE

0 that reference CVE-2026-42208 directly.

CVE-specific rules are not available in this build. Search SigmaHQ ↗

Sigma rules © SigmaHQ, Detection Rule License 1.1; linked, not reproduced.

Am I affected? What do I upgrade to?

From GitHub Security Advisories and OSV

1 package in 1 ecosystem. Main package: litellm.

Upgrade to 1.84.0 or later

Fixes this CVE and 5 other known vulnerabilities in this package (CVE-2026-35029, CVE-2026-40217, +3).

pippip install "litellm>=1.84.0"

First fixed in 1.83.7 for CVE-2026-42208.

Affected versions

If you runUpgrade to
1.81.16 up to 1.83.71.84.0first fix for this CVE: 1.83.7

“Up to” means the second version is the fix and is not affected.

Check your lockfile against all CVEs

What security researchers reported

Not named in any threat report yet

Also mentioned in 50 community threat pulses (AlienVault OTX)

Weaker evidence

Pulses are indicator collections that anyone can publish. A mention is not confirmation of exploitation.

References

6 links, grouped by NVD tag
↑ ↓ chooseEnter openEsc close