LiteLLM JWT authentication bypass vulnerability can lead to account takeover
Start here
OX Security Blog reports that OX Research disclosed an account takeover vulnerability CVE-2026-93355 (CWE-290, CVSS 8.8) in the open-source AI gateway LiteLLM. An attacker can use a legitimately signed JWT to impersonate any existing user, including proxy_admin. LiteLLM unifies over 100 LLM APIs including OpenAI, Anthropic, Azure, Bedrock, Vertex AI, and centrally stores upstream API keys, usage, and virtual keys. The report states that the vulnerability remains unfixed in version 1.100.1.
Generated by AI from reports · Updated 5 days ago
Progress timeline
- OX Security BlogSelectedLiteLLM exposed to CVE-2026-93355 account takeover vulnerability; 1.100.1 still not fixed
OX Research discloses an account takeover vulnerability in LiteLLM, CVE-2026-93355 (CWE-290, CVSS 8.8), where an attacker can use a legitimately signed JWT to impersonate any existing user, including proxy_admin. LiteLLM is an open-source AI gateway that unifies proxying over 100 LLM APIs including OpenAI, Anthropic, Azure, Bedrock, and Vertex AI, and centrally stores upstream API keys, usage, and virtual keys.