CVE-2026-42208: BerriAI LiteLLM SQL Injection Vulnerability

What is known

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.

Business impact

Successful exploitation of CVE-2026-42208, a critical vulnerability (CVSS 9.3) affecting LiteLLM, may affect the confidentiality, integrity or availability of the vulnerable environment. The exact impact depends on the installed version, exposed interfaces and deployment configuration. CISA lists this vulnerability in the Known Exploited Vulnerabilities catalog, so exposed systems should be treated as a priority.

Recommended administrator action

Confirm whether LiteLLM is present and compare installed versions with the vendor advisory and NVD record. Apply the vendor patch or documented mitigation; until remediation is complete, reduce exposure of affected interfaces, review relevant logs and monitor for indicators of exploitation. Where applicable, include the CISA KEV remediation due date of 2026-05-11 in the change plan. DataHouse can support version verification, managed patching, network exposure reduction, log review and backup validation for dedicated, cloud and colocated environments.

Sources

• NVD
• CISA KEV
• Reference
• Reference
• Reference
• Reference
• Reference
• Reference