CVE-2026-55580
HIGH
8,6
Source: [email protected]
Attack Vector: local
Attack Complexity: low
Privileges Required: none
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
Description
AI Translation Available
mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, config.go initializes Security.Enabled to false, and when MCP_SHELL_SEC_CONFIG_FILE is unset, main.go starts the documented bare-binary deployment without a security policy. SecurityValidator.validateCommand in security.go then short-circuits and allows every command supplied to the shell_exec MCP tool, so an LLM connected over stdio can execute unrestricted OS commands as the mcp-shell process user. The README from-source installation and MCP client configuration omit MCP_SHELL_SEC_CONFIG_FILE, making the insecure state the documented default. This issue is fixed in version 0.6.0.
78
Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
StableCommon Consequences
Security Scopes Affected:
Confidentiality
Integrity
Availability
Non-Repudiation
Potential Impacts:
Execute Unauthorized Code Or Commands
Dos: Crash, Exit, Or Restart
Read Files Or Directories
Modify Files Or Directories
Read Application Data
Modify Application Data
Hide Activities
Applicable Platforms
Technologies:
Not Technology-Specific, AI/ML, Web Server
https://github.com/sonirico/mcp-shell/security/advisories/GHSA-f5pj-2738-996m
https://github.com/sonirico/mcp-shell/commit/f31377fce6ec31114e5a4398c0e5270552…
https://github.com/sonirico/mcp-shell/pull/16
https://github.com/sonirico/mcp-shell/releases/tag/v0.6.0
https://github.com/sonirico/mcp-shell/security/advisories/GHSA-f5pj-2738-996m