SEPTEMBER 7, 2026
Live Feed
Back to database
Case File

CVE-2026-54051

CRITICAL · CVSS 9.9 EPSS 0.37% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-07-20 · Last synced 2026-08-19

CyberRota Analysis

AI-Generated

The vulnerability affects the Network-AI multi-agent orchestrator prior to version 5.9.1, where the command allowlist mechanism fails to properly restrict shell command execution, allowing arbitrary command execution through crafted inputs. This critical flaw (CVSS 9.9) poses significant risks, as it could enable attackers to execute malicious commands on the system. Organizations using affected versions should prioritize upgrading to version 5.9.1 or later and review their allowlist configurations to avoid broad wildcard entries that could lead to exploitation.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Detected Signals
code execution

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-54051
Severity
CRITICAL
CVSS
9.9
EPSS
0.37%

Original NVD 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.