CVE-2026-2256 (GCVE-0-2026-2256)
Vulnerability from cvelistv5 – Published: 2026-03-02 20:09 – Updated: 2026-03-03 20:07
VLAI
EPSS
VEX
Title
Command injection vulnerability in ModelScope's ms-agent
Summary
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.
Severity
6.5 (Medium)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-03-03 20:06 UTC
CWE
- CWE-94 Improper Control of Generation of Code ('Code Injection')
- CWE-77 - Improper Neutralization of Special Elements used in a Command ('Command Injection')
Assigner
References
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| ModelScope | ms-agent |
Affected:
0 , ≤ v1.6.0rc1
(custom)
|
guessed |
{
"containers": {
"adp": [
{
"providerMetadata": {
"dateUpdated": "2026-03-02T21:10:07.108Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"url": "https://www.kb.cert.org/vuls/id/431821"
}
],
"title": "CVE Program Container"
},
{
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2026-2256",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-03T20:06:53.906869Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-77",
"description": "CWE-77 Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-03-03T20:07:24.775Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "ms-agent",
"vendor": "ModelScope",
"versions": [
{
"lessThanOrEqual": "v1.6.0rc1",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A command injection vulnerability in ModelScope\u0027s ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "CWE-94 Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-03-02T20:09:11.808Z",
"orgId": "37e5125f-f79b-445b-8fad-9564f167944b",
"shortName": "certcc"
},
"references": [
{
"url": "https://github.com/modelscope/ms-agent"
},
{
"url": "https://www.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use"
},
{
"url": "https://medium.com/@itamar.yochpaz/cve-2026-2256-from-ai-prompt-to-full-system-compromise-a4114c718326"
},
{
"url": "https://github.com/Itamar-Yochpaz/CVE-2026-2256-PoC"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Command injection vulnerability in ModelScope\u0027s ms-agent",
"x_generator": {
"engine": "VINCE 3.0.32",
"env": "prod",
"origin": "https://cveawg.mitre.org/api/cve/CVE-2026-2256"
}
}
},
"cveMetadata": {
"assignerOrgId": "37e5125f-f79b-445b-8fad-9564f167944b",
"assignerShortName": "certcc",
"cveId": "CVE-2026-2256",
"datePublished": "2026-03-02T20:09:11.808Z",
"dateReserved": "2026-02-09T15:23:17.916Z",
"dateUpdated": "2026-03-03T20:07:24.775Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-2256",
"date": "2026-09-20",
"epss": "0.01611",
"percentile": "0.74848"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"product": "ms-agent",
"vendor": "ModelScope",
"versions": [
{
"lessThanOrEqual": "v1.6.0rc1",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"source": "cret@cert.org"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "A command injection vulnerability in ModelScope\u0027s 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."
}
],
"id": "CVE-2026-2256",
"lastModified": "2026-06-17T10:30:38.700",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N",
"version": "3.1"
},
"exploitabilityScore": 3.9,
"impactScore": 2.5,
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-2256",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "yes"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-03T20:06:53.906869Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-03-02T21:16:27.797",
"references": [
{
"source": "cret@cert.org",
"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": "af854a3a-2127-422b-91ae-364da2661108",
"url": "https://www.kb.cert.org/vuls/id/431821"
}
],
"sourceIdentifier": "cret@cert.org",
"vulnStatus": "Awaiting Analysis",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-77"
}
],
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"aggregate_severity": "Moderate",
"current_release_date": "2026-06-28T07:17:36+00:00",
"cve": "CVE-2026-2256",
"id": "CVE-2026-2256",
"initial_release_date": "2026-03-02T20:09:11.808000+00:00",
"product_status:known_affected": "5",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "ModelScope: ModelScope, Red Hat AI Inference Server, Red Hat OpenShift AI: Arbitrary code execution via crafted prompt input",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-2256.json",
"version": "3"
},
"vulnrichment": {
"containers": {
"adp": [
{
"providerMetadata": {
"dateUpdated": "2026-03-02T21:10:07.108Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"url": "https://www.kb.cert.org/vuls/id/431821"
}
],
"title": "CVE Program Container"
},
{
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2026-2256",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-03T20:06:53.906869Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-77",
"description": "CWE-77 Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-03-03T20:07:21.159Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "ms-agent",
"vendor": "ModelScope",
"versions": [
{
"lessThanOrEqual": "v1.6.0rc1",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A command injection vulnerability in ModelScope\u0027s ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "CWE-94 Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-03-02T20:09:11.808Z",
"orgId": "37e5125f-f79b-445b-8fad-9564f167944b",
"shortName": "certcc"
},
"references": [
{
"url": "https://github.com/modelscope/ms-agent"
},
{
"url": "https://www.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use"
},
{
"url": "https://medium.com/@itamar.yochpaz/cve-2026-2256-from-ai-prompt-to-full-system-compromise-a4114c718326"
},
{
"url": "https://github.com/Itamar-Yochpaz/CVE-2026-2256-PoC"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Command injection vulnerability in ModelScope\u0027s ms-agent",
"x_generator": {
"engine": "VINCE 3.0.32",
"env": "prod",
"origin": "https://cveawg.mitre.org/api/cve/CVE-2026-2256"
}
}
},
"cveMetadata": {
"assignerOrgId": "37e5125f-f79b-445b-8fad-9564f167944b",
"assignerShortName": "certcc",
"cveId": "CVE-2026-2256",
"datePublished": "2026-03-02T20:09:11.808Z",
"dateReserved": "2026-02-09T15:23:17.916Z",
"dateUpdated": "2026-03-03T20:07:24.775Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.
Loading…