{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-24158", "assignerOrgId": "9576f279-3576-44b5-a4af-b9a8644b2de6", "state": "PUBLISHED", "assignerShortName": "nvidia", "dateReserved": "2026-01-21T19:09:29.851Z", "datePublished": "2026-03-24T20:26:28.640Z", "dateUpdated": "2026-03-25T14:27:11.988Z"}, "containers": {"cna": {"providerMetadata": {"orgId": "9576f279-3576-44b5-a4af-b9a8644b2de6", "shortName": "nvidia", "dateUpdated": "2026-03-24T20:26:28.640Z"}, "problemTypes": [{"descriptions": [{"lang": "en", "cweId": "CWE-789", "description": "CWE-789 Memory Allocation with Excessive Size Value", "type": "CWE"}]}], "impacts": [{"descriptions": [{"lang": "en", "value": "Denial of Service"}]}], "affected": [{"vendor": "NVIDIA", "product": "Triton Inference Server", "platforms": ["All"], "versions": [{"status": "affected", "version": "All versions prior to 26.01"}], "defaultStatus": "unaffected"}], "descriptions": [{"lang": "en", "value": "NVIDIA Triton Inference Server contains a vulnerability in the HTTP endpoint where an attacker may cause a denial of service by providing a large compressed payload. A successful exploit of this vulnerability may lead to denial of service.", "supportingMedia": [{"type": "text/html", "base64": true, "value": "NVIDIA Triton Inference Server contains a vulnerability in the HTTP endpoint where an attacker may cause a denial of service by providing a large compressed payload. A successful exploit of this vulnerability may lead to denial of service."}]}], "references": [{"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-24158"}, {"url": "https://www.cve.org/CVERecord?id=CVE-2026-24158"}, {"url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5790"}], "metrics": [{"format": "CVSS", "scenarios": [{"lang": "en", "value": "GENERAL"}], "cvssV3_1": {"version": "3.1", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "availabilityImpact": "HIGH", "baseSeverity": "HIGH", "baseScore": 7.5, "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H"}}], "source": {"discovery": "UNKNOWN"}, "x_generator": {"engine": "NVIDIA PSIRT"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-03-25T14:24:10.152143Z", "id": "CVE-2026-24158", "options": [{"Exploitation": "none"}, {"Automatable": "yes"}, {"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": "2026-03-25T14:27:11.988Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"cna": {"source": {"discovery": "UNKNOWN"}, "impacts": [{"descriptions": [{"lang": "en", "value": "Denial of Service"}]}], "metrics": [{"format": "CVSS", "cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 7.5, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/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": "Triton Inference Server", "versions": [{"status": "affected", "version": "All versions prior to 26.01"}], "platforms": ["All"], "defaultStatus": "unaffected"}], "references": [{"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-24158"}, {"url": "https://www.cve.org/CVERecord?id=CVE-2026-24158"}, {"url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5790"}], "x_generator": {"engine": "NVIDIA PSIRT"}, "descriptions": [{"lang": "en", "value": "NVIDIA Triton Inference Server contains a vulnerability in the HTTP endpoint where an attacker may cause a denial of service by providing a large compressed payload. A successful exploit of this vulnerability may lead to denial of service.", "supportingMedia": [{"type": "text/html", "value": "NVIDIA Triton Inference Server contains a vulnerability in the HTTP endpoint where an attacker may cause a denial of service by providing a large compressed payload. A successful exploit of this vulnerability may lead to denial of service.", "base64": true}]}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-789", "description": "CWE-789 Memory Allocation with Excessive Size Value"}]}], "providerMetadata": {"orgId": "9576f279-3576-44b5-a4af-b9a8644b2de6", "shortName": "nvidia", "dateUpdated": "2026-03-24T20:26:28.640Z"}}, "adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-24158", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "yes"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-03-25T14:24:10.152143Z"}}}], "providerMetadata": {"shortName": "CISA-ADP", "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "dateUpdated": "2026-03-25T14:24:14.793Z"}}]}, "cveMetadata": {"cveId": "CVE-2026-24158", "state": "PUBLISHED", "dateUpdated": "2026-03-24T20:26:28.640Z", "dateReserved": "2026-01-21T19:09:29.851Z", "assignerOrgId": "9576f279-3576-44b5-a4af-b9a8644b2de6", "datePublished": "2026-03-24T20:26:28.640Z", "assignerShortName": "nvidia"}, "dataVersion": "5.2"}

{"cveTags": [], "descriptions": [{"lang": "en", "value": "NVIDIA Triton Inference Server contains a vulnerability in the HTTP endpoint where an attacker may cause a denial of service by providing a large compressed payload. A successful exploit of this vulnerability may lead to denial of service."}], "id": "CVE-2026-24158", "lastModified": "2026-03-25T15:41:58.280", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 7.5, "baseSeverity": "HIGH", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "version": "3.1"}, "exploitabilityScore": 3.9, "impactScore": 3.6, "source": "psirt@nvidia.com", "type": "Secondary"}]}, "published": "2026-03-24T21:16:27.997", "references": [{"source": "psirt@nvidia.com", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-24158"}, {"source": "psirt@nvidia.com", "url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5790"}, {"source": "psirt@nvidia.com", "url": "https://www.cve.org/CVERecord?id=CVE-2026-24158"}], "sourceIdentifier": "psirt@nvidia.com", "vulnStatus": "Awaiting Analysis", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-789"}], "source": "psirt@nvidia.com", "type": "Primary"}]}

{}

{"affected": [{"configurations": [{"platform": ["all"], "status": "affected", "versions": {"scheme": "generic", "value": "[0,26.01)"}}], "enrichment": {"confidence": 100.0, "confidence_source": "matching", "scores": [{"score": 100.0, "source": "matching"}]}, "original": {"product": "Triton Inference Server", "source": "cna", "vendor": "NVIDIA"}, "product": "triton_inference_server", "vendor": "nvidia"}], "analysis": {"en": {"generated_at": "2026-03-24T21:21:24.557539+00:00", "value": {"mitigation_remediation": ["Check NVIDIA\u2019s official resources for an updated Triton Inference Server release or advisory.", "Review server logs for abnormal request patterns or unusually large payloads.", "Configure network firewalls or API gateways to limit the size of incoming HTTP requests.", "If possible, disable or restrict the HTTP endpoint during off\u2011peak hours.", "Implement rate limiting or request throttling to prevent resource exhaustion.", "Consider upgrading to a newer Triton Inference Server version once a patch is available."], "summary": {"action": "Mitigate", "impact": "Denial of Service"}, "threat_synthesis": {"affected_systems": "NVIDIA Triton Inference Server. No specific product version information appears in the advisory, so all installations that expose the HTTP interface are potentially impacted.", "description_and_impact": "The Triton Inference Server\u2019s HTTP endpoint is vulnerable to resource exhaustion when a client supplies a large compressed payload. Sending such a payload consumes memory and processing time, causing legitimate requests to fail. The flaw is classified as CWE\u2011789 and results in a denial of service that can disrupt availability for all users of the affected service.", "risk_and_exploitability": "With a CVSS base score of 7.5, this bug represents a high risk to service availability. Because the HTTP interface is publicly accessible, an attacker can trigger the vulnerability from any network location that can reach the server, without authentication or elevated privileges. No exploits have yet been reported in the CISA KEV catalog, and EPSS data is unavailable, meaning it is unclear how frequently this vulnerability is targeted. Nonetheless, the lack of required credentials lowers the barrier for exploitation, making it a viable threat for denial of service attacks."}}}}, "created": "2026-03-25T11:45:56.227477+00:00", "title": "Denial of Service via Large Compressed Payload in Triton Inference Server HTTP Endpoint", "updated": "2026-03-25T20:57:22.165849+00:00", "vendors": ["nvidia", "nvidia$PRODUCT$triton_inference_server"]}