CVE-2026-24158
Nvidia Triton Inference Server ≤ 26.01
Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HSummary
CVE-2026-24158 is a high-severity Memory Allocation with Excessive Size Value (CWE-789) vulnerability in Nvidia Triton Inference Server. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Endpoint Denial of Service (T1499); ranked at the 34th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
The strongest mitigations our analysis identified map to SI-10 (Information Input Validation) and SC-6 (Resource Availability) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-24158 is a vulnerability in the HTTP endpoint of NVIDIA Triton Inference Server, where an attacker can cause a denial of service by providing a large compressed payload. This issue, associated with CWE-789 (Uncontrolled Memory Allocation), received a CVSS v3.1 base score of 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H), highlighting its high availability impact with no requirements for privileges or user interaction. The vulnerability was published on 2026-03-24.
A remote, unauthenticated attacker can exploit this vulnerability over the network by sending a specially crafted large compressed payload to the affected HTTP endpoint, leading to denial of service on the Triton Inference Server. Successful exploitation results in service disruption but does not allow confidentiality or integrity violations.
Mitigation details are available in official advisories, including NVIDIA's security bulletin at https://nvidia.custhelp.com/app/answers/detail/a_id/5790, as well as entries on the NVD at https://nvd.nist.gov/vuln/detail/CVE-2026-24158 and CVE.org at https://www.cve.org/CVERecord?id=CVE-2026-24158. Security practitioners should review these sources for patch availability and recommended remediation steps.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-15013
Vulnerability Data
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.
- CWE(s)
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Input validation directly rejects or bounds untrusted size values before any allocation occurs.
Resource quotas and priority allocation limit the system-wide impact of an oversized request.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly prevent coding flaws that trust unvalidated size values for allocations.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing in development can detect and block excessive allocation flaws before deployment.
Secure development lifecycle includes input validation and size checks that prevent unbounded allocations.
Application security requirements mandate bounds checking on size parameters to avoid excessive memory allocation.
Secure architecture principles require resource-limit enforcement that mitigates uncontrolled memory requests.
Secure coding standards directly prohibit allocating memory from untrusted size values without validation.
Capacity management monitors overall resource use but does not prevent individual allocation bugs.