CVE-2026-58195: high-severity vulnerability in ruvnet agentic-flow
Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync
Published
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
21Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 8.8epss 0.6%
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:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Affected products
ruvnet · agentic-flowReferences
https://github.com/ruvnet/agentic-flow/commit/0c2ec967736a8b6b85832c6bae2a3e74989705echttps://github.com/ruvnet/agentic-flow/issues/169https://github.com/ruvnet/agentic-flow/pull/170https://github.com/ruvnet/agentic-flow/security/advisories/GHSA-vcv2-r9jh-99m5https://github.com/ruvnet/ruflo/issues/2414https://github.com/ruvnet/ruflo/pull/2415https://github.com/ruvnet/ruflo/releases/tag/v3.12.4