Threat intelligence · CVEs & news
Published: 05/08/2026 · Modified: 10/26/2026
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process. The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host. This issue has been patched in version 1.83.7.
Requires: network access, privileged account, target conditions · Does not require: user interaction
Not enough data to detail.
Not enough data to detail.
Does not require: user interaction.
Not enough data to detail.
Confidentiality: highIntegrity: highAvailability: high
Also affects components beyond the vulnerable one.
The “Requires/Does not require” line and the confidentiality, integrity and availability impact come from the official CVSS vector. Method, applicability and mitigation are an automatic summary of the NVD description, public exploitation sources (Metasploit, Nuclei, Exploit-DB) and the CVE record via CIRCL (advisories and fixed version), linked under “References and technical detail”. Community reports come from CIRCL sightings and are unverified.