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

published 2026-06-19 4 mo ago modified 2026-10-24 15 d ago also GHSA-vcv2-r9jh-99m5 , EUVD-2026-45256

cvss: 8.8; version 3.1, CNA
cisa kev: Not listed; not in CISA's catalog
epss: 0.6%; EPSS 0.6% chance of exploitation in 30 days, percentile 46%
public exploits: 0; none known

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.

Patch / fix

fixed in 1 links 4

npm agentic-flow 2.0.14

github.com/ruvnet/agentic-flow@0c2ec96 commit
github.com/ruvnet/agentic-flow#170 pull request
github.com/ruvnet/ruflo#2415 pull request
github.com/ruvnet/ruflo/releases/tag/v3.12.4 release

CISA SSVC

Exploitation: Proof of concept is public
Automatable: no
Technical impact: total
Assessed: 3 mo ago (2026-07-17)

Exploit prediction

0.56% chance of exploitation in the next 30 days, higher than 46% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

github.com https://github.com/ruvnet/agentic-flow/security/advisories/GHSA-vcv2-r9jh-99m5 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by	version	score	vector
CNA	3.1	8.8	CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
GitHub	3.1	8.8	CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Affected packages

ecosystem	package	affected	fixed in
npm	agentic-flow	<2.0.14	2.0.14

Affected products

ruvnet agentic-flow

Classification

Weakness

CWE-78 Improper Neutralization of Special Elements used in an OS Command

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

Summary