Widely used LLM gateway LiteLLM exposed to high-risk vulnerabilities
Warning Over High-Risk Vulnerabilities in Widely Used LLM Gateway Tool
Check Point disclosed two high-risk vulnerabilities in the LLM gateway LiteLLM, CVE-2026-35029 and CVE-2026-59823, where any user with an account on the gateway could gain administrator privileges and take over the system. The vulnerabilities affect versions before 1.83.9 and are fixed in 1.83.9 and later. Check Point stated that CVE-2026-35029 exploits a missing authorization check to modify runtime configuration, allowing remote code execution by loading malicious Python modules from cloud storage; CVE-2026-59823 redirects the gateway's outbound requests through server-side request forgery, exposing AI providers' API keys. LiteLLM is an open-source tool with nearly 100,000 monthly downloads, used to connect enterprise AI applications to providers such as OpenAI, Google, and Anthropic. Check Point recommends upgrading to the latest version and auditing account permissions and rotating API keys.
The LiteLLM gateway centrally stores API keys for various AI providers. Two vulnerabilities disclosed by Check Point could let any account gain administrator privileges, so users should check their versions and permission configurations accordingly.