Skip to main content

Mondoo Vulnerability Intelligence

Curated by Mondoo Research, enhanced with AI

Resources

Search Vulnerabilities
Trending CVEs
Browse Ecosystems
Terminology
Blog

Open Source

cnquery
cnspec

Star us on GitHub!

Company

Mondoo Platform
About
Contact

© 2026 Mondoo, Inc.

Privacy Policy Terms of Service Imprint

Vulnerability Intelligence

Vulnerability IntelligenceCVE-2026-2256

CVE-2026-2256

MEDIUM6.5

Command injection vulnerability in ModelScope's ms-agent

Published Mar 2, 2026

Modified 1 weeks ago

Details

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.

References

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.cve.org/CVERecord?id=CVE-2026-2256

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

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

CVSS Analysis

CVSS v3.1

6.5

Exploitability

Attack Vector

NetworkAV:N

Attack Complexity

LowAC:L

Privileges Required

NonePR:N

User Interaction

NoneUI:N

Scope

Scope

UnchangedS:U

Impact

Confidentiality

LowC:L

Integrity

LowI:L

Availability

NoneA:N

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

Ecosystems

Timeline

PublishedMar 2, 2026

ModifiedMar 3, 2026

CVE-2026-2256 | Mondoo Vulnerability Intelligence