Every CVE Search/ Get API key

CVE-2026-42208

LiteLLM: SQL injection in Proxy API key verification

9.3 CriticalIn KEVPublic exploitFix available

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.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
Low
Privileges needed
None
User interaction
None

What an attacker can affect

Confidentiality
High
Integrity
High
Availability
High

Exploit likelihood

89.4%Up 89.3 points since May 8, 2026
90%50%10%1%

What each source reports

CVE List Score used 9.3

LiteLLM: SQL injection in Proxy API key verification

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.

Record
CVE-2026-42208
CVSS 4.0
9.3 CriticalCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CVSS 3.1
9.8 CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness
CWE-89, CWE-89
Updated
2026-11-02
EUVDEUVD-2026-28503 9.3

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.

Record
EUVD-2026-28503
CVSS 4.0
9.3 CriticalCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Updated
2026-11-02
GitHub AdvisoriesGHSA-r75f-5x8p-qvmc 9.3

LiteLLM has SQL Injection in Proxy API key verification

Impact

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.

Patches

Fixed in 1.83.7. The caller-supplied value is now always passed to the database as a separate parameter. Upgrade to 1.83.7 or later.

Workarounds

If upgrading is not immediately possible, set disable_error_logs: true under general_settings. This removes the path through which unauthenticated input reaches the vulnerable query.

References

Discovery Credit: Tencent YunDing Security Lab

Record
GHSA-r75f-5x8p-qvmc
CVSS 4.0
9.3 CriticalCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CVSS 3.1
9.8 CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness
CWE-89
Updated
2026-11-02
CISA KEV No score

BerriAI LiteLLM SQL Injection Vulnerability

BerriAI LiteLLM contains a SQL injection vulnerability that allows an attacker to read data from the proxy's database and potentially modify it, leading to unauthorized access to the proxy and the credentials it manages.

Record
CVE-2026-42208
Weakness
CWE-89
Updated
2026-11-02
NVD 9.3

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.

Record
CVE-2026-42208
CVSS 4.0
9.3 CriticalCVSS: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
CVSS 3.1
9.8 CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS 3.1
9.8 CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness
CWE-89
Updated
2026-11-02
OSV 9.3

LiteLLM: SQL injection in Proxy API key verification

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.

Record
CVE-2026-42208
CVSS 4.0
9.3 CriticalCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Weakness
CWE-89
Updated
2026-11-02
OSVGHSA-r75f-5x8p-qvmc 9.3

LiteLLM has SQL Injection in Proxy API key verification

Impact

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.

Patches

Fixed in 1.83.7. The caller-supplied value is now always passed to the database as a separate parameter. Upgrade to 1.83.7 or later.

Workarounds

If upgrading is not immediately possible, set disable_error_logs: true under general_settings. This removes the path through which unauthenticated input reaches the vulnerable query.

References

Discovery Credit: Tencent YunDing Security Lab

Record
GHSA-r75f-5x8p-qvmc
CVSS 4.0
9.3 CriticalCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CVSS 3.1
9.8 CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness
CWE-89
Updated
2026-11-02
OSVPYSEC-2026-391 9.3

LiteLLM has SQL Injection in Proxy API key verification

Impact

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.

Patches

Fixed in 1.83.7. The caller-supplied value is now always passed to the database as a separate parameter. Upgrade to 1.83.7 or later.

Workarounds

If upgrading is not immediately possible, set disable_error_logs: true under general_settings. This removes the path through which unauthenticated input reaches the vulnerable query.

References

Discovery Credit: Tencent YunDing Security Lab

Record
PYSEC-2026-391
CVSS 4.0
9.3 CriticalCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CVSS 3.1
9.8 CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Updated
2026-11-02

Affected products

Affected packages

Affected packages
PackageAffectedFixed
litellm
PyPI
 1.81.16 up to 1.83.7
1.83.7
litellm
PyPI
 1.81.16 up to 1.83.7, plus listed versions
1.82.01.82.11.82.21.82.31.82.4
Show 9 moreShow less
1.82.51.82.61.83.01.83.11.83.21.83.31.83.41.83.51.83.6
1.83.7

Public exploits

Links only. Every CVE stores no exploit code.

Public exploits
SourceLinkDate
PoC in GitHubimjdl/CVE-2026-42208_lab2026-04-28
PoC in GitHub0xBlackash/CVE-2026-422082026-05-03
PoC in GitHubZeltoc/threat-intel-brief-cve-2026-42208-litellm2026-05-10
PoC in GitHubrootdirective-sec/CVE-2026-42208-Lab2026-05-10
PoC in GitHubridhinva/litellm-sqli-scanner2026-05-22
PoC in GitHubHAERIN-L/poc_cve-2026-422082026-05-30
MetasploitBerriAI LiteLLM Proxy Pre-Auth SQL Injection Scanner2026-04-20
NucleiLiteLLM - SQL Injection

History

History
RecordedChangedSources
exploitation, exploits
first indexedCVE List, EUVD, GitHub Advisories, CISA KEV, Metasploit, Nuclei, NVD, OSV, PoC in GitHub

Dates are when Every CVE recorded each change. Upstream dates may differ.

In short

CVE-2026-42208 is a critical vulnerability (CVSS 9.3) in Berriai Litellm, published April 24, 2026. CISA lists it as known to be exploited, since May 8, 2026. EUVD reports exploitation since May 8, 2026. Public exploit code exists. EPSS puts the chance of exploitation in the next 30 days at 89.4%, the 99th percentile. Fixed in litellm 1.83.7.

References

Show 6 moreShow less
Pages All vulnerabilities Browse Docs Sources Guide Get API key
MoveEnter Open