Authenticated command execution via unvalidated MCP stdio configuration
Published Jul 15, 2026 · Updated Jul 15, 2026
Command injection in LiteLLM before 1.83.6-nightly allows remote authenticated users to execute operating system commands via MCP requests. The MCP server create, update, and preview paths pass a JSON-supplied stdio command directly to StdioServerParameters, which spawns it as a subprocess without validation. A valid LiteLLM API key and access to the affected endpoints are required; commands run with the privileges and data access of the LiteLLM process.
Summary
What happened
Command injection in LiteLLM before 1.83.6-nightly allows remote authenticated users to execute operating system commands via MCP requests. The MCP server create, update, and preview paths pass a JSON-supplied stdio command directly to StdioServerParameters, which spawns it as a subprocess without validation. A valid LiteLLM API key and access to the affected endpoints are required; commands run with the privileges and data access of the LiteLLM process.
The record
- CVE
- CVE-2026-30623
- Published
- Jul 15, 2026
- Updated
- Jul 15, 2026
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-77, T1059
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Jul 15, 2026CVE publishedPublication date reported by the CVE source.
- Jul 15, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- OX Security MCP STDIO command-injection advisoryproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo