CVE-2026-42208
criticalpriority · act · 90OT risk · criticalKEV · exploitedEPSS 0.894 · 100 %ileexploit · functionalDEEUNLUSadded 2026-05-08remediate by 2026-05-11
required action Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
EPSS · scored 2026-10-26
BerriAI LiteLLM SQL Injection Vulnerability
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.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
exploits (7)
Public proof-of-concept and weaponised exploit code.
- 0xBlackash/CVE-2026-42208CVE-2026-40487PoC · poc_in_github
- HAERIN-L/poc_cve-2026-42208HAERIN-L/poc_cve-2026-42208PoC · poc_in_github
- imjdl/CVE-2026-42208_labCVE-2026-42208 labPoC · poc_in_github
affected products (7)
Products and version ranges known to be affected.
advisories (4)
Vendor and ecosystem advisories describing this.
- NCSC-2026-0137Kwetsbaarheden verholpen in LiteLLM door BerriAINL2026-05-11csaf · ncsc_nlNL
BerriAI heeft kwetsbaarheden verholpen in LiteLLM, specifiek in versies 1.74.2 tot en met 1.83.6.
- WID-SEC-W-2026-1288LiteLLM: Mehrere SchwachstellenDeutsch2026-04-27csaf · cert_bundDE
Ein Angreifer kann mehrere Schwachstellen in LiteLLM ausnutzen, um einen SQL-Injection-Angriff durchzuführen und sich unbefugten Zugriff zu verschaffen oder um beliebigen Programmcode mit den Rechten des Dienstes auszuführen
- GHSA-r75f-5x8p-qvmcLiteLLM has SQL Injection in Proxy API key verification2026-04-24ghsa · osvUS
### 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 - Patched release: [`v1.83.7-stable`](https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable) **Discovery Credit**: Tencent YunDing Security Lab
- PYSEC-2026-391LiteLLM has SQL Injection in Proxy API key verification2026-06-29vendor · osvUS
### 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 - Patched release: [`v1.83.7-stable`](https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable) **Discovery Credit**: Tencent YunDing Security Lab
also known as (6)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (10)
External citations — patches, advisories, analysis.
- https://github.com/BerriAI/litellm/releasesPatchcnnvd
- https://nvd.nist.gov/vuln/detail/CVE-2026-42208cnnvd
- https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stableenisa_euvd
- https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmcenisa_euvd
- https://access.redhat.com/security/cve/CVE-2026-42208Third Party Advisorynvd
- https://bugzilla.redhat.com/show_bug.cgi?id=2463965MitigationThird Party Advisorynvd
- https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stableProductRelease Notesnvd
- https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmcMitigationPatchVendor Advisorynvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan