CVE-2026-47475 - Vulnerability Details - OpenCVE

NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.

No CVSS v4.0

Attack Vector Local

Attack Complexity Low

Privileges Required None

Scope Unchanged

Confidentiality Impact None

Integrity Impact None

Availability Impact High

User Interaction None

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

Exploitation none

Automatable no

Technical Impact partial

Vendors	Products
Nvidia	Tensorrt-llm

No data.

No data.

References

Link	Providers
https://nvd.nist.gov/vuln/detail/CVE-2026-47475
https://www.cve.org/CVERecord?id=CVE-2026-47475

History

Fri, 17 Jul 2026 05:30:00 +0000

Type	Values Removed	Values Added
Metrics		ssvc `{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}`

Thu, 16 Jul 2026 13:45:00 +0000

Type	Values Removed	Values Added
Title		TensorRT-LLM OpenAI API Assertion Failure Denial of Service

Wed, 15 Jul 2026 16:00:00 +0000

Type	Values Removed	Values Added
First Time appeared		Nvidia Nvidia tensorrt-llm
Vendors & Products		Nvidia Nvidia tensorrt-llm

Tue, 14 Jul 2026 20:30:00 +0000

Type	Values Removed	Values Added
Description		NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.
Weaknesses		CWE-617
References		https://nvd.nist.gov/vuln/detail/CVE-2026-47475 https://www.cve.org/CVERecord?id=CVE-2026-47475
Metrics		cvssV3_1 `{'score': 6.2, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'}`

MITRE

Status: PUBLISHED

Assigner: nvidia

Published: 2026-07-14T20:08:43.131Z

Updated: 2026-07-15T14:18:36.942Z

Reserved: 2026-05-19T19:55:38.728Z

Link: CVE-2026-47475

Vulnrichment

Updated: 2026-07-15T14:18:34.171Z

NVD

No data.

Redhat

No data.

{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-47475", "assignerOrgId": "9576f279-3576-44b5-a4af-b9a8644b2de6", "state": "PUBLISHED", "assignerShortName": "nvidia", "dateReserved": "2026-05-19T19:55:38.728Z", "datePublished": "2026-07-14T20:08:43.131Z", "dateUpdated": "2026-07-15T14:18:36.942Z"}, "containers": {"cna": {"providerMetadata": {"orgId": "9576f279-3576-44b5-a4af-b9a8644b2de6", "shortName": "nvidia", "dateUpdated": "2026-07-14T20:08:43.131Z"}, "problemTypes": [{"descriptions": [{"lang": "en", "cweId": "CWE-617", "description": "CWE-617 Reachable Assertion", "type": "CWE"}]}], "impacts": [{"descriptions": [{"lang": "en", "value": "Denial of Service"}]}], "affected": [{"vendor": "NVIDIA", "product": "TensorRT-LLM", "versions": [{"status": "affected", "version": "0.0", "lessThanOrEqual": "v1.3.0 rc15", "versionType": "custom"}], "defaultStatus": "unaffected"}], "descriptions": [{"lang": "en", "value": "NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.", "supportingMedia": [{"type": "text/html", "base64": false, "value": "NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service."}]}], "references": [{"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-47475"}, {"url": "https://www.cve.org/CVERecord?id=CVE-2026-47475"}], "metrics": [{"format": "CVSS", "scenarios": [{"lang": "en", "value": "GENERAL"}], "cvssV3_1": {"version": "3.1", "attackVector": "LOCAL", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "availabilityImpact": "HIGH", "baseSeverity": "MEDIUM", "baseScore": 6.2, "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H"}}], "source": {"discovery": "EXTERNAL"}, "x_generator": {"engine": "Vulnogram 1.0.2"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-07-15T14:18:30.583932Z", "id": "CVE-2026-47475", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-07-15T14:18:36.942Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-47475", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-07-15T14:18:30.583932Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-07-15T14:18:34.171Z"}}], "cna": {"source": {"discovery": "EXTERNAL"}, "impacts": [{"descriptions": [{"lang": "en", "value": "Denial of Service"}]}], "metrics": [{"format": "CVSS", "cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 6.2, "attackVector": "LOCAL", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "NONE"}, "scenarios": [{"lang": "en", "value": "GENERAL"}]}], "affected": [{"vendor": "NVIDIA", "product": "TensorRT-LLM", "versions": [{"status": "affected", "version": "0.0", "versionType": "custom", "lessThanOrEqual": "v1.3.0 rc15"}], "defaultStatus": "unaffected"}], "references": [{"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-47475"}, {"url": "https://www.cve.org/CVERecord?id=CVE-2026-47475"}], "x_generator": {"engine": "Vulnogram 1.0.2"}, "descriptions": [{"lang": "en", "value": "NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.", "supportingMedia": [{"type": "text/html", "value": "NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.", "base64": false}]}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-617", "description": "CWE-617 Reachable Assertion"}]}], "providerMetadata": {"orgId": "9576f279-3576-44b5-a4af-b9a8644b2de6", "shortName": "nvidia", "dateUpdated": "2026-07-14T20:08:43.131Z"}}}, "cveMetadata": {"cveId": "CVE-2026-47475", "state": "PUBLISHED", "dateUpdated": "2026-07-15T14:18:36.942Z", "dateReserved": "2026-05-19T19:55:38.728Z", "assignerOrgId": "9576f279-3576-44b5-a4af-b9a8644b2de6", "datePublished": "2026-07-14T20:08:43.131Z", "assignerShortName": "nvidia"}, "dataVersion": "5.2"}