Arbitrary command execution via MCP parameter interpolation
Published Jul 17, 2026 · Updated Jul 17, 2026
OS command injection in Agentic-Flow before 2.0.14 allows remote attackers to execute arbitrary commands through crafted MCP tool arguments. Affected MCP server tools interpolate agent, task, name, language, and agentdb values into double-quoted execSync command strings, allowing shell metacharacters to escape the intended argument. Exploitation requires malicious content to reach an MCP tool or an exposed unauthenticated HTTP/SSE transport, and commands run with the MCP server user privileges.
Summary
What happened
OS command injection in Agentic-Flow before 2.0.14 allows remote attackers to execute arbitrary commands through crafted MCP tool arguments. Affected MCP server tools interpolate agent, task, name, language, and agentdb values into double-quoted execSync command strings, allowing shell metacharacters to escape the intended argument. Exploitation requires malicious content to reach an MCP tool or an exposed unauthenticated HTTP/SSE transport, and commands run with the MCP server user privileges.
The record
- CVE
- CVE-2026-58195
- Published
- Jul 17, 2026
- Updated
- Jul 17, 2026
- Vendor
- ruvnet
- Product
- Agentic-Flow
- Classifications
- CWE-78, T1059.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 17, 2026CVE publishedPublication date reported by the CVE source.
- Jul 17, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 2.0.14
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-vcv2-r9jh-99m5 proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo