CVE-2026-24222 (GCVE-0-2026-24222)
Vulnerability from cvelistv5 – Published: 2026-04-28 17:46 – Updated: 2026-04-29 15:11
VLAI
EPSS
VEX
Summary
NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandbox creation. A successful exploit of this vulnerability might lead to information disclosure.
Severity
8.6 (High)
SSVC
Exploitation: none
Automatable: yes
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-04-29 13:51 UTC
CWE
- CWE-497 - Exposure of Sensitive System Information to an Unauthorized Control Sphere
Assigner
References
Impacted products
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-24222",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-04-29T13:51:53.035168Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-04-29T15:11:41.945Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"platforms": [
"All"
],
"product": "NemoClaw",
"vendor": "NVIDIA",
"versions": [
{
"status": "affected",
"version": "All versions prior to v0.0.18"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": true,
"type": "text/html",
"value": "NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandbox creation. A successful exploit of this vulnerability might lead to information disclosure."
}
],
"value": "NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandbox creation. A successful exploit of this vulnerability might lead to information disclosure."
}
],
"impacts": [
{
"descriptions": [
{
"lang": "en",
"value": "Information disclosure"
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-497",
"description": "CWE-497 Exposure of Sensitive System Information to an Unauthorized Control Sphere",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-04-28T17:46:37.015Z",
"orgId": "9576f279-3576-44b5-a4af-b9a8644b2de6",
"shortName": "nvidia"
},
"references": [
{
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-24222"
},
{
"url": "https://www.cve.org/CVERecord?id=CVE-2026-24222"
},
{
"url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5837"
}
],
"source": {
"discovery": "UNKNOWN"
},
"x_generator": {
"engine": "NVIDIA PSIRT"
}
}
},
"cveMetadata": {
"assignerOrgId": "9576f279-3576-44b5-a4af-b9a8644b2de6",
"assignerShortName": "nvidia",
"cveId": "CVE-2026-24222",
"datePublished": "2026-04-28T17:46:37.015Z",
"dateReserved": "2026-01-21T19:09:36.964Z",
"dateUpdated": "2026-04-29T15:11:41.945Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-24222",
"date": "2026-09-29",
"epss": "0.00395",
"percentile": "0.31089"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "unaffected",
"platforms": [
"All"
],
"product": "NemoClaw",
"vendor": "NVIDIA",
"versions": [
{
"status": "affected",
"version": "All versions prior to v0.0.18"
}
]
}
],
"source": "psirt@nvidia.com"
}
],
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:nvidia:nemoclaw:*:*:*:*:*:*:*:*",
"matchCriteriaId": "48E4DA43-5E4A-419B-BD40-D2DF1FB1F035",
"versionEndExcluding": "0.0.18",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandbox creation. A successful exploit of this vulnerability might lead to information disclosure."
}
],
"id": "CVE-2026-24222",
"lastModified": "2026-06-17T10:22:48.837",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
"version": "3.1"
},
"exploitabilityScore": 3.9,
"impactScore": 4.0,
"source": "psirt@nvidia.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-24222",
"options": [
{
"exploitation": "none"
},
{
"automatable": "yes"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-04-29T13:51:53.035168Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-04-28T19:36:45.517",
"references": [
{
"source": "psirt@nvidia.com",
"tags": [
"US Government Resource"
],
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-24222"
},
{
"source": "psirt@nvidia.com",
"tags": [
"Vendor Advisory"
],
"url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5837"
},
{
"source": "psirt@nvidia.com",
"tags": [
"Third Party Advisory"
],
"url": "https://www.cve.org/CVERecord?id=CVE-2026-24222"
}
],
"sourceIdentifier": "psirt@nvidia.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-497"
}
],
"source": "psirt@nvidia.com",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"current_release_date": "2026-04-29T20:48:02+00:00",
"cve": "CVE-2026-24222",
"id": "CVE-2026-24222",
"initial_release_date": "2026-01-01T00:00:00+00:00",
"product_status:known_not_affected": "1",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "CVE-2026-24222",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-24222.json",
"version": "3"
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-24222",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-04-29T13:51:53.035168Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-04-29T13:51:57.727Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"platforms": [
"All"
],
"product": "NemoClaw",
"vendor": "NVIDIA",
"versions": [
{
"status": "affected",
"version": "All versions prior to v0.0.18"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": true,
"type": "text/html",
"value": "NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandbox creation. A successful exploit of this vulnerability might lead to information disclosure."
}
],
"value": "NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandbox creation. A successful exploit of this vulnerability might lead to information disclosure."
}
],
"impacts": [
{
"descriptions": [
{
"lang": "en",
"value": "Information disclosure"
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-497",
"description": "CWE-497 Exposure of Sensitive System Information to an Unauthorized Control Sphere",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-04-28T17:46:37.015Z",
"orgId": "9576f279-3576-44b5-a4af-b9a8644b2de6",
"shortName": "nvidia"
},
"references": [
{
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-24222"
},
{
"url": "https://www.cve.org/CVERecord?id=CVE-2026-24222"
},
{
"url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5837"
}
],
"source": {
"discovery": "UNKNOWN"
},
"x_generator": {
"engine": "NVIDIA PSIRT"
}
}
},
"cveMetadata": {
"assignerOrgId": "9576f279-3576-44b5-a4af-b9a8644b2de6",
"assignerShortName": "nvidia",
"cveId": "CVE-2026-24222",
"datePublished": "2026-04-28T17:46:37.015Z",
"dateReserved": "2026-01-21T19:09:36.964Z",
"dateUpdated": "2026-04-29T15:11:41.945Z",
"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…
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…