CVE-2026-24220 (GCVE-0-2026-24220)
Vulnerability from cvelistv5 – Published: 2026-07-14 20:05 – Updated: 2026-07-15 14:19
VLAI
EPSS
VEX
Summary
NVIDIA TensorRT-LLM for any platform contains a vulnerability in visual gen server, where an attacker could cause an unsafe deserialization by unauthorized zeroMQ deserialization. A successful exploit of this vulnerability might lead to code execution.
Severity
6.4 (Medium)
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-07-15 14:19 UTC
CWE
- CWE-502 - Deserialization of Untrusted Data
Assigner
References
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| NVIDIA | TensorRT-LLM |
Affected:
0.0 , ≤ v1.3.0 rc11
(custom)
|
guessed |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-24220",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-15T14:19:34.893063Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-15T14:19:44.134Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "TensorRT-LLM",
"vendor": "NVIDIA",
"versions": [
{
"lessThanOrEqual": "v1.3.0 rc11",
"status": "affected",
"version": "0.0",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "NVIDIA TensorRT-LLM for any platform contains a vulnerability in visual gen server, where an attacker could cause an unsafe deserialization by unauthorized zeroMQ deserialization. A successful exploit of this vulnerability might lead to code execution."
}
],
"value": "NVIDIA TensorRT-LLM for any platform contains a vulnerability in visual gen server, where an attacker could cause an unsafe deserialization by unauthorized zeroMQ deserialization. A successful exploit of this vulnerability might lead to code execution."
}
],
"impacts": [
{
"descriptions": [
{
"lang": "en",
"value": "Code Execution"
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 6.4,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "HIGH",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502 Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-14T20:05:36.549Z",
"orgId": "9576f279-3576-44b5-a4af-b9a8644b2de6",
"shortName": "nvidia"
},
"references": [
{
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-24220"
},
{
"url": "https://www.cve.org/CVERecord?id=CVE-2026-24220"
}
],
"source": {
"discovery": "EXTERNAL"
},
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "9576f279-3576-44b5-a4af-b9a8644b2de6",
"assignerShortName": "nvidia",
"cveId": "CVE-2026-24220",
"datePublished": "2026-07-14T20:05:36.549Z",
"dateReserved": "2026-01-21T19:09:35.635Z",
"dateUpdated": "2026-07-15T14:19:44.134Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-24220",
"date": "2026-09-16",
"epss": "0.00323",
"percentile": "0.25355"
},
"nvd": "{\"cve\":{\"id\":\"CVE-2026-24220\",\"sourceIdentifier\":\"psirt@nvidia.com\",\"published\":\"2026-07-14T21:16:43.773\",\"lastModified\":\"2026-07-15T16:23:03.437\",\"vulnStatus\":\"Awaiting Analysis\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"NVIDIA TensorRT-LLM for any platform contains a vulnerability in visual gen server, where an attacker could cause an unsafe deserialization by unauthorized zeroMQ deserialization. A successful exploit of this vulnerability might lead to code execution.\"}],\"affected\":[{\"source\":\"psirt@nvidia.com\",\"affectedData\":[{\"vendor\":\"NVIDIA\",\"product\":\"TensorRT-LLM\",\"defaultStatus\":\"unaffected\",\"versions\":[{\"version\":\"0.0\",\"lessThanOrEqual\":\"v1.3.0 rc11\",\"versionType\":\"custom\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"psirt@nvidia.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":6.4,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"LOCAL\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"HIGH\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":0.5,\"impactScore\":5.9}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-07-15T14:19:34.893063Z\",\"id\":\"CVE-2026-24220\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"psirt@nvidia.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-502\"}]}],\"references\":[{\"url\":\"https://nvd.nist.gov/vuln/detail/CVE-2026-24220\",\"source\":\"psirt@nvidia.com\"},{\"url\":\"https://www.cve.org/CVERecord?id=CVE-2026-24220\",\"source\":\"psirt@nvidia.com\"}]}}",
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-24220\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-07-15T14:19:34.893063Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-07-15T14:19:39.326Z\"}}], \"cna\": {\"source\": {\"discovery\": \"EXTERNAL\"}, \"impacts\": [{\"descriptions\": [{\"lang\": \"en\", \"value\": \"Code Execution\"}]}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 6.4, \"attackVector\": \"LOCAL\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"HIGH\", \"confidentialityImpact\": \"HIGH\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}], \"affected\": [{\"vendor\": \"NVIDIA\", \"product\": \"TensorRT-LLM\", \"versions\": [{\"status\": \"affected\", \"version\": \"0.0\", \"versionType\": \"custom\", \"lessThanOrEqual\": \"v1.3.0 rc11\"}], \"defaultStatus\": \"unaffected\"}], \"references\": [{\"url\": \"https://nvd.nist.gov/vuln/detail/CVE-2026-24220\"}, {\"url\": \"https://www.cve.org/CVERecord?id=CVE-2026-24220\"}], \"x_generator\": {\"engine\": \"Vulnogram 1.0.2\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"NVIDIA TensorRT-LLM for any platform contains a vulnerability in visual gen server, where an attacker could cause an unsafe deserialization by unauthorized zeroMQ deserialization. A successful exploit of this vulnerability might lead to code execution.\", \"supportingMedia\": [{\"type\": \"text/html\", \"value\": \"NVIDIA TensorRT-LLM for any platform contains a vulnerability in visual gen server, where an attacker could cause an unsafe deserialization by unauthorized zeroMQ deserialization. A successful exploit of this vulnerability might lead to code execution.\", \"base64\": false}]}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-502\", \"description\": \"CWE-502 Deserialization of Untrusted Data\"}]}], \"providerMetadata\": {\"orgId\": \"9576f279-3576-44b5-a4af-b9a8644b2de6\", \"shortName\": \"nvidia\", \"dateUpdated\": \"2026-07-14T20:05:36.549Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-24220\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-07-15T14:19:44.134Z\", \"dateReserved\": \"2026-01-21T19:09:35.635Z\", \"assignerOrgId\": \"9576f279-3576-44b5-a4af-b9a8644b2de6\", \"datePublished\": \"2026-07-14T20:05:36.549Z\", \"assignerShortName\": \"nvidia\"}",
"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…