Intel

AIKIDO-2026-10152

@qwen-code/qwen-code is vulnerable to Command Injection

Command Injection Pre-CVE
Found by Aikido Intel before public disclosure or CVE publication.
Published Feb 10, 2026

55

Medium Risk

This Affects:

JS@qwen-code/qwen-code
0.0.1 - 0.8.2
Fixed in 0.9.0
Are you affected? Scan for Free

TL;DR

Affected versions of this package allow newline-separated command injection where only the first line is validated. An attacker can place a multi-line instruction containing a benign read-only command followed by a malicious one, bypassing safety checks because the parser did not treat \n/\r\n as command separators. As a result, validation approves the first command while subsequent arbitrary commands execute silently without user confirmation.

Who does this affect?

You are affected if you are using a version that falls within the vulnerable range. Requires user interaction / untrusted input in CLI context.

Background info

@qwen-code/qwen-code is vulnerable to Command Injection in versions 0.0.1 - 0.8.2.

How to fix this

Upgrade the @qwen-code/qwen-code library to the patch version.