CVE-2026-54051
Received Received - Intake

Command Injection Vulnerability in Network-AI Multi-Agent Orchestrator

Publication date: 2026-07-20

Last updated on: 2026-07-20

Assigner: GitHub, Inc.

Description
Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to version 5.9.1, the agent sandbox gates shell commands behind an allowlist (`SandboxPolicy.isCommandAllowed`), which THREAT_MODEL.md calls the main control against a compromised agent (Adversary 3.2). The allowlist glob-matches the whole command string, but `ShellExecutor` runs that string through `/bin/sh -c`. So any wildcard allow such as `git *`, `npm *` or `node *` also matches `git status; <anything>`, and a scoped command becomes arbitrary execution. The issue is fixed in v5.9.1. `ShellExecutor` now executes via `spawn(file, args, { shell: false })` using a quote-aware parsed argv, so no shell is invoked. `SandboxPolicy.isCommandAllowed` and the new `SandboxPolicy.tokenizeCommand` reject any unquoted shell metacharacter (`; & | $ ` ` ` ( ) < > { }` newline) or unterminated quote before the allowlist glob match; quoted metacharacters are preserved as literal argument data. Users should upgrade to `[email protected]` or later. As defense in depth, avoid broad wildcard allowlist entries such as `node *` / `npm *` which are direct code execution by design.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-07-20
Last Modified
2026-07-20
Generated
2026-07-21
AI Q&A
2026-07-20
EPSS Evaluated
N/A
NVD
CVE-2026-54051
EUVD
EUVD-2026-46003

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
jovancoding network-ai to 5.9.1 (exc)
jovancoding network-ai From 5.9.1 (inc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-78 The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

CVE-2026-54051 is a critical shell command injection flaw in Network-AI versions 5.9.0 and earlier. The vulnerability occurs because the sandbox's allowlist checks the full command string as a glob pattern (e.g., 'git *' matches 'git status; id'), but the command is executed via a shell (/bin/sh -c). This allows attackers to bypass restrictions by appending malicious commands using shell metacharacters like semicolons. The issue is fixed in v5.9.1 by replacing shell execution with spawn() and adding command tokenization to reject unquoted metacharacters.

Detection Guidance

Check Network-AI version with: npm list network-ai. If version is below 5.9.1, the system is vulnerable. Review agent configuration files for broad wildcard allowlist entries like 'git *', 'npm *', or 'node *' which could indicate potential bypass risks.

Impact Analysis

This vulnerability allows an attacker with access to a compromised agent to execute arbitrary commands on the system running Network-AI. This could lead to full system compromise, data theft, or disruption of services. The impact includes potential loss of confidentiality, integrity, and availability of the system. The high CVSS score (9.9) reflects the severe risk, requiring only low attack complexity and no privileges or user interaction.

Compliance Impact

This vulnerability could lead to unauthorized access to sensitive data, violating GDPR's data protection requirements and HIPAA's security rules for protected health information. Organizations using vulnerable versions may face compliance violations, legal penalties, and reputational damage due to potential data breaches or unauthorized system access.

Mitigation Strategies

Upgrade Network-AI to version 5.9.1 or later using: npm update network-ai. Remove broad wildcard allowlist entries and replace them with specific allowed commands. Restart all agents after upgrade to ensure the fix is active.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-54051. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart