CVE-2026-2256

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 v3 6.5 MEDIUM

6.5^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 3.9 / Impact : 2.5

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact LOW

Integrity Impact LOW

Availability Impact NONE

Scope UNCHANGED

References

Link	Resource
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

Configurations

No configuration.

History

17 Jun 2026, 10:30

Type	Values Removed	Values Added
Summary		(es) Una vulnerabilidad de inyección de comandos existe en las versiones v1.6.0rc1 y anteriores de ms-agent de ModelScope, permitiendo a un atacante ejecutar comandos arbitrarios del sistema operativo a través de una entrada manipulada derivada de un prompt.

03 Mar 2026, 20:16

Type	Values Removed	Values Added
CVSS	v2 : ~~unknown~~ v3 : ~~unknown~~	v2 : unknown v3 : 6.5
CWE		CWE-77

02 Mar 2026, 22:16

Type	Values Removed	Values Added
References		() https://www.kb.cert.org/vuls/id/431821 -

02 Mar 2026, 21:16

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-03-02 21:16

Updated : 2026-06-17 10:30

NVD link : CVE-2026-2256

Mitre link : CVE-2026-2256

CVE.ORG link : CVE-2026-2256

JSON object : View

Products Affected

No product.

CWE

CWE-77

Improper Neutralization of Special Elements used in a Command ('Command Injection')

{"id": "CVE-2026-2256", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-2256", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "yes"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-03-03T20:06:53.906869Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 6.5, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N", "integrityImpact": "LOW", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "NONE", "confidentialityImpact": "LOW"}, "impactScore": 2.5, "exploitabilityScore": 3.9}]}, "affected": [{"source": "cret@cert.org", "affectedData": [{"vendor": "ModelScope", "product": "ms-agent", "versions": [{"status": "affected", "version": "0", "versionType": "custom", "lessThanOrEqual": "v1.6.0rc1"}]}]}], "published": "2026-03-02T21:16:27.797", "references": [{"url": "https://github.com/Itamar-Yochpaz/CVE-2026-2256-PoC", "source": "cret@cert.org"}, {"url": "https://github.com/modelscope/ms-agent", "source": "cret@cert.org"}, {"url": "https://medium.com/@itamar.yochpaz/cve-2026-2256-from-ai-prompt-to-full-system-compromise-a4114c718326", "source": "cret@cert.org"}, {"url": "https://www.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use", "source": "cret@cert.org"}, {"url": "https://www.kb.cert.org/vuls/id/431821", "source": "af854a3a-2127-422b-91ae-364da2661108"}], "vulnStatus": "Awaiting Analysis", "weaknesses": [{"type": "Secondary", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "description": [{"lang": "en", "value": "CWE-77"}]}], "descriptions": [{"lang": "en", "value": "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."}, {"lang": "es", "value": "Una vulnerabilidad de inyecci\u00f3n de comandos existe en las versiones v1.6.0rc1 y anteriores de ms-agent de ModelScope, permitiendo a un atacante ejecutar comandos arbitrarios del sistema operativo a trav\u00e9s de una entrada manipulada derivada de un prompt."}], "lastModified": "2026-06-17T10:30:38.700", "sourceIdentifier": "cret@cert.org"}