CVE-2026-54051: Jovancoding Network-AI OS command injection in agent sandbox

CVE-2026-54051 · Severity: critical · CVSS 9.9 · Published 2026-07-20

Network-AI is a tool used to manage and coordinate multiple AI agents. A security flaw in its sandbox allows these agents to bypass command restrictions and run unauthorized programs on the host server. If an agent is compromised or malicious, it could take full control of the underlying system, potentially leading to data theft or service disruption.

Technologies: Jovancoding Network-AI, network-ai (npm). Vendors: Jovancoding, npm.

Quick answers

Is CVE-2026-54051 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-54051 being exploited in the wild.
How severe is CVE-2026-54051?
Critical severity, with a CVSS score of 9.9, published 20 July 2026.
Which products and versions are affected?
Jovancoding Network-AI < 5.9.1; network-ai (npm) SEMVER:introduced=0,fixed=5.9.1.
Is there a fix for CVE-2026-54051?
Yes. network-ai (npm): upgrade to 5.9.1 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-54051 attacked?
It is attacked over the network, in a software library.
Am I affected by CVE-2026-54051?
Check whether you run Jovancoding Network-AI or network-ai (npm) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

  • network-ai (npm): upgrade to 5.9.1 or later
    npm install network-ai@5.9.1

Technical details

Network-AI prior to version 5.9.1 is vulnerable to OS command injection (CWE-78) within its agent sandbox. The `SandboxPolicy.isCommandAllowed` function uses glob-matching to validate commands against an allowlist, but the `ShellExecutor` subsequently executes these strings using `/bin/sh -c` (or `cmd.exe /c`). Because the allowlist matching does not account for shell metacharacters, an attacker can append malicious commands (e.g., using `;`, `&`, or `|`) to a string that otherwise matches a wildcard pattern like `git *`. This results in arbitrary code execution with the privileges of the orchestrator process. The vulnerability is fixed in v5.9.1 by switching to `spawn` with `shell: false` and implementing a quote-aware tokenizer that rejects unquoted shell metacharacters.

Affected products

  • Jovancoding Network-AI < 5.9.1

Identifiers

  • CVE-2026-54051
  • GHSA-qw6v-5fcf-5666

Timeline

  • 2026-06-02: advisory: GitHub Security Advisory published
  • 2026-07-20: disclosed: CVE-2026-54051 published to NVD
  • 2026-07-20: patched: Fixed in version 5.9.1

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.