CVE-2026-58195: CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in ruvnet agentic-flow
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.
AI Analysis
Technical Summary
CVE-2026-58195 is an OS command injection vulnerability (CWE-78) in the ruvnet agentic-flow product. Prior to version 2.0.14, several MCP server tools interpolate user-influenced parameters such as agent, task, name, language, and agentdb directly into shell command strings passed to Node.js execSync(). This improper neutralization of special elements enables an attacker to execute arbitrary OS commands with the privileges of the MCP server user. The vulnerability affects multiple source files related to standalone stdio, fastmcp servers, and orchestration tools. The issue is resolved in agentic-flow version 2.0.14.
Potential Impact
Successful exploitation allows an unauthenticated remote attacker (no privileges required) to execute arbitrary operating system commands with the privileges of the MCP server user. This can lead to full system compromise, including confidentiality, integrity, and availability impacts. The CVSS 3.1 base score is 8.8 (high severity) reflecting network attack vector, low attack complexity, no privileges required, user interaction required, and high impact on confidentiality, integrity, and availability.
Mitigation Recommendations
Upgrade agentic-flow to version 2.0.14 or later, where this OS command injection vulnerability is fixed. There is no official patch or workaround available for earlier versions. Until upgraded, avoid exposing MCP server tools to untrusted input or users. Patch status is not explicitly confirmed beyond the fix in 2.0.14; check vendor advisories for updates.
CVE-2026-58195: CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in ruvnet agentic-flow
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.
CVSS v3.1
Score 8.8high
Affected software
pkg:github/ruvnet/agentic-flowRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-58195 is an OS command injection vulnerability (CWE-78) in the ruvnet agentic-flow product. Prior to version 2.0.14, several MCP server tools interpolate user-influenced parameters such as agent, task, name, language, and agentdb directly into shell command strings passed to Node.js execSync(). This improper neutralization of special elements enables an attacker to execute arbitrary OS commands with the privileges of the MCP server user. The vulnerability affects multiple source files related to standalone stdio, fastmcp servers, and orchestration tools. The issue is resolved in agentic-flow version 2.0.14.
Potential Impact
Successful exploitation allows an unauthenticated remote attacker (no privileges required) to execute arbitrary operating system commands with the privileges of the MCP server user. This can lead to full system compromise, including confidentiality, integrity, and availability impacts. The CVSS 3.1 base score is 8.8 (high severity) reflecting network attack vector, low attack complexity, no privileges required, user interaction required, and high impact on confidentiality, integrity, and availability.
Mitigation Recommendations
Upgrade agentic-flow to version 2.0.14 or later, where this OS command injection vulnerability is fixed. There is no official patch or workaround available for earlier versions. Until upgraded, avoid exposing MCP server tools to untrusted input or users. Patch status is not explicitly confirmed beyond the fix in 2.0.14; check vendor advisories for updates.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-06-29T17:09:25.871Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a5b5eb32d1edb114c7fb4e7
Added to database: 07/18/2026, 11:08:35 UTC
Last enriched: 07/18/2026, 11:56:58 UTC
Last updated: 07/18/2026, 13:34:58 UTC
Views: 5
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.