Home / Apr 30, 2026 / Story
0
#6 BleepingComputer general April 28, 2026 at 21:07 UTC

Hackers are exploiting a critical LiteLLM pre-auth SQLi flaw

By Bill Toulas

AI Summary

CVE-2026-42208, a critical SQL injection vulnerability in BerriAI's LiteLLM large language model gateway, is being actively exploited within 36 hours of public disclosure. The CVSS 9.3 flaw allows attackers to read and modify database content in LiteLLM proxy deployments used for managing AI model access.

Relevance score: 82.0/100

# More from April 30