CVE-2026-2256
MEDIUM EPSS 72.9%
Published Mar 2, 20263mo ago · Modified Jun 17, 20261w ago
6.5 CVSS 3.1
Published Mar 2, 2026 3mo ago
Last Modified Jun 17, 2026 1w ago
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.
CVSS Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction None
Scope Unchanged
Confidentiality Low
Integrity Low
Availability None
Threat Intelligence
EPSS Exploit Probability
72.9% percentile
Exploit & Patch Status
No Known Exploit
No Patch Available
Weaknesses 1
CWE-77 Command Injection Injection
References 5
- github.com https://github.com/Itamar-Yochpaz/CVE-2026-2256-PoC
- github.com https://github.com/modelscope/ms-agent
- medium.com https://medium.com/@itamar.yochpaz/cve-2026-2256-from-ai-prompt-to-full-system-compromise-a4114c718326
- hiddenlayer.com https://www.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use
- kb.cert.org https://www.kb.cert.org/vuls/id/431821
Remediation
No remediation data recorded yet
Check vendor advisories and the NVD entry for patch availability.