Skip to main content
← All vulnerabilities
CVE-2026-58195GHSA-VCV2-R9JH-99M5

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

Published
Last modified
published
Not listed in CISA KEV
Fix
Fixed in 2.0.14
None on Exploit-DB, Metasploit or GitHub
  • Exploitation: poc
  • Automatable: no
  • Technical impact: total

Summary

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.

Timeline

  1. CVE published
  2. CISA SSVC assessment

    Exploitation: poc · Automatable: no · Technical impact: total

  3. Record last updated

Affected versions

  • ruvnet agentic-flow

    fixed in 2.0.14

  • agentic-flownpm

    fixed in 2.0.14

References 7

GitHub · ruvnet/agentic-flow

GitHub · ruvnet/ruflo