LiteLLM, a proxy server for LLM APIs, contained an SQL injection vulnerability (CWE-89) in versions 1.81.16 through 1.83.6. The vulnerability occurs because the proxy's database query for API key validation concatenates the caller-supplied key directly into the SQL statement rather than using parameterized queries. An unauthenticated attacker can exploit this by sending a specially crafted Authorization header to any LLM API endpoint, reaching the vulnerable query through the error-handling path. This can lead to unauthorized reading and modification of the proxy's database, potentially compromising access credentials. The vulnerability is addressed in version 1.83.7.

The vulnerability allows unauthenticated attackers to perform SQL injection attacks against the LiteLLM proxy server's database. This can lead to unauthorized disclosure and modification of sensitive data, including proxy credentials, which may result in unauthorized access to the proxy and its managed resources. The CVSS 4.0 base score is 9.3, indicating a critical severity with network attack vector, no required privileges or user interaction, and high impact on confidentiality, integrity, and availability.

A patch fixing this vulnerability is available in LiteLLM version 1.83.7. Users should upgrade to version 1.83.7 or later to remediate this issue. Since this is not a cloud service, remediation depends on applying the vendor's update. Patch status is not explicitly stated beyond the version fix, so users should consult the vendor's advisory or release notes for confirmation and further guidance.