8.7 HIGH
- CVSS version (CVSS): 4.0
- Attack Vector (AV): Network (N)
- Attack Complexity (AC): Low (L)
- Attack Requirement (AT): Present (P)
- Privileges Required (PR): Low (L)
- User Interaction (UI): None (N)
- Vulnerable System Impact Confidentiality (VC): High (H)
- Vulnerable System Impact Integrity (VI): High (H)
- Vulnerable System Impact Availability (VA): High (H)
- Subsequent System Impact Confidentiality (SC): High (H)
- Subsequent System Impact Integrity (SI): None (N)
- Subsequent System Impact Availability (SA): None (N)
- Modified Attack Vector (MAV): Network (N)
- Modified Attack Complexity (MAC): Low (L)
- Modified Attack Requirement (MAT): Present (P)
- Modified Privileges Required (MPR): Low (L)
- Modified User Interaction (MUI): None (N)
- Modified Vulnerable System Impact Confidentiality (MVC): High (H)
- Modified Vulnerable System Impact Integrity (MVI): High (H)
- Modified Vulnerable System Impact Availability (MVA): High (H)
- Modified Subsequent System Impact Confidentiality (MSC): High (H)
- Modified Subsequent System Impact Integrity (MSI): Negligible (N)
- Modified Subsequent System Impact Availability (MSA): Negligible (N)
- Safety (S): Not Defined (X)
- Automatable (AU): Not Defined (X)
- Recovery (R): Not Defined (X)
- Value Density (V): Not Defined (X)
- Vulnerability Response Effort (RE): Not Defined (X)
- Provider Urgency (U): Not Defined (X)
- Confidentiality Req. (CR): Not Defined (X)
- Integrity Req. (IR): Not Defined (X)
- Availability Req. (AR): Not Defined (X)
- Exploit Maturity (E): Not Defined (X)
Activity log
- Created suggestion
LiteLLM: Authenticated command execution via MCP stdio test endpoints
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.
References
-
https://github.com/BerriAI/litellm/security/advisories/GHSA-v4p8-mg3p-g94g x_refsource_CONFIRM
-
https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable x_refsource_MISC
Affected products
- ==>= 1.74.2, < 1.83.7
Matching in nixpkgs
pkgs.litellm
Use any LLM as a drop in replacement for gpt-3.5-turbo. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs)
pkgs.python312Packages.litellm
Use any LLM as a drop in replacement for gpt-3.5-turbo. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs)
pkgs.python313Packages.litellm
Use any LLM as a drop in replacement for gpt-3.5-turbo. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs)
pkgs.python314Packages.litellm
Use any LLM as a drop in replacement for gpt-3.5-turbo. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs)
Package maintainers
-
@happysalada Raphael Megzari <raphael@megzari.com>