CVE-2026-2256

EUVD-2026-9257
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.
Command Injection
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
NISTPrimary
6.5 MEDIUM
NETWORK
LOW
NONE
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
Awaiting analysis
This vulnerability is currently awaiting analysis.
Base Score
CVSS 3.x
EPSS Score
Percentile: Unknown
Common Weakness Enumeration
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.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use
https://www.kb.cert.org/vuls/id/431821