LiteLLM Vulnerability Exploited Shortly After Disclosure, Highlights Cybersecurity Risks
A critical vulnerability in the open-source AI gateway LiteLLM was exploited shortly after its public disclosure. Identified as CVE-2026-42208, the vulnerability involves an SQL injection during the proxy API key verification process, allowing unauthorized access to sensitive database information. The flaw was disclosed on April 20, and within 36 hours, attackers began exploiting it to target database tables containing API keys and credentials. The attacks were automated, with attempts occurring 21 minutes apart, indicating a high level of sophistication. LiteLLM has since released a patch to address the vulnerability, urging users to update their systems to prevent further exploitation.