| Component | LiteLLM |
| Severity | critical (CVSS 9.8) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| Published (NVD) | 2026-07-15 |
| Last modified | 2026-07-16 |
| Affected versions | not published yet, see the advisory |
| Fixed in | see the vendor advisory |
| Weakness | CWE-77 |
| CISA KEV | not listed |
NVD description
LiteLLM 1.18.10 contains a remote code execution vulnerability in its MCP server creation functionality. The application allows users to add MCP servers via a JSON configuration specifying arbitrary command and args values. LiteLLM executes these values on the host without validation, enabling attackers to run arbitrary operating system commands. Successful exploitation may result in remote code execution with the privileges of the LiteLLM process.
What to do
- NVD lists no fixed version yet: follow the vendor advisory below and keep LiteLLM off the public internet until a fix ships.
- Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-30623
- https://docs.litellm.ai/blog/mcp-stdio-command-injection-april-2026
- https://github.com/BerriAI/litellm
- https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/
Read more
Other LiteLLM CVEs
A vulnerability has been found in BerriAI LiteLLM up to 1.94.0. This affects the function get_secret of the file secret_managers/main.py of...
A flaw has been found in BerriAI LiteLLM up to 1.95.0. Affected by this issue is the function ui_view_session_spend_logs of the file litellm...
LiteLLM contains a weak authentication vulnerability that allows an attacker holding a valid JWT from the configured identity provider to au...
BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated u...
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.9, an authenticated LiteLLM Proxy caller...
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated...