CVE-2026-123022
Deferred Deferred - Pending Action

Command Injection in AgentScope MCP Workspace API

Publication date: 2026-11-05

Last updated on: 2026-11-05

Assigner: VulDB

Description
A vulnerability was detected in agentscope-ai AgentScope up to 2.0.11. The impacted element is the function subprocess.Popen of the file src/agentscope/mcp/_config.py of the component MCP Workspace API. The manipulation of the argument command results in os command injection. The attack may be launched remotely. The exploit is now public and may be used. The pull request to fix this issue awaits acceptance.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-11-05
Last Modified
2026-11-05
Generated
2026-11-05
AI Q&A
2026-11-05
EPSS Evaluated
N/A
NVD
CVE-2026-123022
EUVD
EUVD-2026-117439

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-77 The product constructs all or part of a command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended command when it is sent to a downstream component.
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 unauthenticated remote code execution vulnerability in AgentScope up to version 2.0.11. It allows attackers to execute arbitrary OS commands via the MCP Workspace API by manipulating the command argument in subprocess.Popen within src/agentscope/mcp/_config.py. The attack occurs through a crafted HTTP request to the /workspace/mcp endpoint without requiring authentication.

Detection Guidance

Check AgentScope logs for suspicious POST requests to /workspace/mcp with unusual command fields. Monitor for unexpected process execution by the AgentScope service user. Use network traffic inspection to detect unauthenticated API calls to the MCP endpoint.

Impact Analysis

An attacker could gain full control of the server running AgentScope, allowing file access, data theft, privilege escalation, denial of service, or lateral movement within the network. Commands execute with the privileges of the AgentScope service user, potentially compromising sensitive data or systems.

Compliance Impact

This vulnerability likely violates compliance requirements for data protection (GDPR, HIPAA) due to unauthorized access to sensitive data, potential data breaches, and lack of proper access controls. Organizations using affected versions may face regulatory penalties and must remediate immediately.

Mitigation Strategies
  • Restrict the /workspace/mcp endpoint to localhost or trusted networks.
  • Implement server-side authentication for the MCP API endpoint.
  • Deploy the opt-in allowlist for stdio commands if available.
  • Block or disable the vulnerable MCP stdio workspace configuration.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-123022. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart

Security Radar

News mentioning this vulnerability
Loading related security news...