CVE-2026-55157
Received Received - Intake

OS Command Injection in Token Optimizer MCP

Publication date: 2026-09-28

Last updated on: 2026-09-28

Assigner: GitHub, Inc.

Description
Token Optimizer MCP measures token savings per AI coding agent, optimizes context, and shares a live local knowledge graph across 16 CLI clients. Prior to version 5.1.0, token-optimizer-mcp is vulnerable to OS command injection in the smart_user tool. Any MCP client that can call the smart_user tool can execute arbitrary shell commands through the username argument of the get-user-info operation. The commands execute with the privileges of the user running the token-optimizer-mcp server. This issue has been patched in version 5.1.0.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-28
Last Modified
2026-09-28
Generated
2026-09-28
AI Q&A
2026-09-28
EPSS Evaluated
N/A
NVD
CVE-2026-55157
EUVD
EUVD-2026-88397

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
ooples token_optimizer_mcp to 5.1.0 (exc)
ooples token_optimizer_mcp 5.1.0

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-78 The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This is an OS command injection vulnerability in the token-optimizer-mcp package. It affects the smart_user tool's get-user-info operation where the username argument is directly used in a shell command without proper sanitization. Attackers can inject arbitrary commands through the username parameter, which executes with the privileges of the user running the MCP server.

Detection Guidance

Check for unusual processes or files created under /tmp that may indicate command execution. Monitor logs for suspicious smart_user tool invocations with crafted usernames containing command substitutions like $(...) or backticks. Review MCP client interactions with the token-optimizer-mcp server for unexpected username inputs.

Impact Analysis

An attacker could execute arbitrary shell commands on your system with the same privileges as the user running the token-optimizer-mcp server. This could lead to unauthorized file access, data theft, or system compromise. The vulnerability allows full command execution, including creating files or running malicious scripts.

Compliance Impact

This vulnerability could lead to unauthorized access to sensitive data, violating GDPR and HIPAA requirements for data protection and access controls. A successful exploit may result in data breaches, non-compliance with security controls, and potential legal consequences for failing to protect personal or health information.

Mitigation Strategies

Upgrade to version 5.1.0 or later of token-optimizer-mcp if available. If no patch exists, disable the smart_user tool or restrict access to trusted MCP clients only. Implement input validation to sanitize the username argument before processing.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-55157. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart