Skip to content
OpenAdvisories
High · 8.8 CVE-2026-58195 EUVD-2026-45256GHSA-vcv2-r9jh-99m5

Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync

Published Jul 17, 2026 · Updated Jul 17, 2026 · Assigned by GitHub_M

Description

Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts, src/mcp/fastmcp/servers/http-sse.ts, src/mcp/fastmcp/servers/poc-stdio.ts, src/mcp/fastmcp/tools/agent/{execute,list,parallel}.ts, src/mcp/fastmcp/tools/swarm/orchestrate.ts, and src/mcp/fastmcp/tools/hooks/pretrain.ts interpolated attacker-influenceable tool parameters such as agent, task, name, language, and agentdb directly into shell command strings passed to execSync(), allowing arbitrary OS command execution with the privileges of the MCP server user. This issue is fixed in version 2.0.14.

Affected products

VendorProductAffectedFixed
ruvnet agentic-flow < 2.0.14 —

Affected packages

EcosystemPackageAffectedFixedRecord
npm agentic-flow < 2.0.14 2.0.14 GHSA-vcv2-r9jh-99m5

References