Back to feed
EUVD-2026-9257 · Published Mar 2, 2026
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.
Technologies
Ms-Agent Ms-Agent
Weaknesses
CWE-77
CVSS scores
- v3.16.5
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
MITRE ATT&CK
InferredWhere this vulnerability fits in an attack
Initial Access
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
- https://nvd.nist.gov/vuln/detail/CVE-2026-2256
Potentially impacted assets
See if this affects your attack surface
