Severity by source
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Primary rating from NVD · only source for this CVE.
CVSS VectorNVD
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Lifecycle Timeline
4DescriptionCVE.org
A security flaw has been discovered in Agions taskflow-ai up to 2.1.8. This impacts an unknown function of the file src/mcp/server/handlers.ts of the component terminal_execute. Performing a manipulation results in os command injection. The attack is possible to be carried out remotely. Upgrading to version 2.1.9 will fix this issue. The patch is named c1550b445b9f24f38c4414e9a545f5f79f23a0fe. Upgrading the affected component is recommended. The vendor was contacted early, responded in a very professional manner and quickly released a fixed version of the affected product.
AnalysisAI
Remote OS command injection in Agions taskflow-ai up to version 2.1.8 allows authenticated remote attackers to execute arbitrary operating system commands via manipulation of the terminal_execute component in src/mcp/server/handlers.ts, with CVSS 6.3 reflecting moderate severity. Vendor-released patch is available in version 2.1.9 (commit c1550b445b9f24f38c4414e9a545f5f79f23a0fe), and the vendor responded promptly to early notification.
Technical ContextAI
This vulnerability is a classic OS command injection flaw (CWE-78) in the Model Context Protocol (MCP) server's terminal execution handler. The terminal_execute function in src/mcp/server/handlers.ts fails to properly sanitize or validate user-supplied input before passing it to operating system command execution functions, allowing attackers to inject shell metacharacters or shell commands. The affected product is Agions taskflow-ai (CPE: cpe:2.3:a:agions:taskflow-ai:*:*:*:*:*:*:*:*), which appears to be an AI workflow orchestration tool that integrates MCP server capabilities for task execution. Command injection at the MCP server layer is particularly dangerous because it can lead to full system compromise depending on the privileges under which the MCP server process runs.
RemediationAI
Upgrade immediately to taskflow-ai version 2.1.9 or later, which includes the security fix via commit c1550b445b9f24f38c4414e9a545f5f79f23a0fe. The patched version is available as a GitHub release at https://github.com/Agions/taskflow-ai/releases/tag/v2.1.9. If immediate upgrade is not feasible, restrict network access to the taskflow-ai MCP server to trusted internal networks only and audit authentication credentials to ensure only authorized users can invoke terminal_execute operations. Review recent audit logs for any terminal_execute API calls from taskflow-ai instances still on 2.1.8 or earlier to identify potential exploitation.
Same weakness CWE-78 – OS Command Injection
View allSame technique Command Injection
View allShare
External POC / Exploit Code
Leaving vuln.today
EUVD-2026-20830