CVE-2026-4944 (GCVE-0-2026-4944)
Vulnerability from cvelistv5 – Published: 2026-05-28 18:04 – Updated: 2026-05-28 19:47
VLAI
EPSS
VEX
Title
Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control
Summary
vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user's explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted.
Severity
8.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-05-28 19:46 UTC
CWE
- CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| vllm-project | vllm-project/vllm |
Affected:
unspecified , ≤ latest
(custom)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-4944",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-05-28T19:46:54.159975Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-05-28T19:47:23.664Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "vllm-project/vllm",
"vendor": "vllm-project",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user\u0027s explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22 Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-05-28T18:04:05.371Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf"
}
],
"source": {
"advisory": "97f706f7-a852-49b2-a4eb-76811e611daf",
"discovery": "EXTERNAL"
},
"title": "Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2026-4944",
"datePublished": "2026-05-28T18:04:05.371Z",
"dateReserved": "2026-03-26T23:52:08.858Z",
"dateUpdated": "2026-05-28T19:47:23.664Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-4944",
"date": "2026-10-03",
"epss": "0.00996",
"percentile": "0.61393"
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-4944",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-05-28T19:46:54.159975Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-05-28T19:47:16.494Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "vllm-project/vllm",
"vendor": "vllm-project",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user\u0027s explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22 Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-05-28T18:04:05.371Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf"
}
],
"source": {
"advisory": "97f706f7-a852-49b2-a4eb-76811e611daf",
"discovery": "EXTERNAL"
},
"title": "Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2026-4944",
"datePublished": "2026-05-28T18:04:05.371Z",
"dateReserved": "2026-03-26T23:52:08.858Z",
"dateUpdated": "2026-05-28T19:47:23.664Z",
"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…