CVE-2026-2256

6.5 MEDIUM

Published: March 02, 2026 Modified: March 03, 2026

Description

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

AI Explanation

Get an AI-powered plain-language explanation of this vulnerability and remediation steps.

CVSS v3.x Details

0.0 Low Medium High Critical 10.0

Vector String

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N

References to Advisories, Solutions, and Tools

Patch Vendor Advisory Exploit Third Party Advisory

https://github.com/Itamar-Yochpaz/CVE-2026-2256-PoC

Source: cret@cert.org

https://github.com/modelscope/ms-agent

Source: cret@cert.org

https://medium.com/@itamar.yochpaz/cve-2026-2256-from-ai-prompt-to-full-system-compromise-a4114c718326

Source: cret@cert.org

https://www.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use

Source: cret@cert.org

https://www.kb.cert.org/vuls/id/431821

Source: af854a3a-2127-422b-91ae-364da2661108

5 reference(s) from NVD

Quick Stats

CVSS v3 Score

6.5 / 10.0

EPSS (Exploit Probability)

2.3%

85th percentile

Exploitation Status

Not in CISA KEV

Weaknesses (CWE)

CWE-77

Related CVEs