CVE-2026-2256

Severity CVSS v4.0:

Pending analysis

Type:

CWE-77 Command Injection

Publication date:

02/03/2026

Last modified:

03/03/2026

Description

A command injection vulnerability in ModelScope&#39;s ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input.

Impact

Vector 3.x

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N CVSS v3.1 Severity and Metrics:

Base Score: 6.50 MEDIUM
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N

Attack Vector (AV): Network
Attack Complexity (AC): Low
Privileges Required (PR): None
User Interaction (UI): None
Scope (S): Unchanged
Confidentiality (C): Low
Integrity (I): Low
Availability (A): None

Base Score 3.x

6.50

Severity 3.x

MEDIUM

References to Advisories, Solutions, and Tools

https://github.com/Itamar-Yochpaz/CVE-2026-2256-PoC
https://github.com/modelscope/ms-agent
https://medium.com/@itamar.yochpaz/cve-2026-2256-from-ai-prompt-to-full-system-compromise-a4114c718326
https://www.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use
https://www.kb.cert.org/vuls/id/431821