Cyber Resilience

CVE-2025-23318

Memory Safety in Nvidia Triton Inference Server ≤ 25.07

Memory Safety
Published
06 August 2025
Modified
17 June 2026
Patch / advisory
View advisory
CVSS Score v3.1 8.1
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS Score 0.0069 50th percentile
Risk Priority 60 floored blend · peak EPSS

Summary

CVE-2025-23318 is a high-severity Buffer Access with Incorrect Length Value (CWE-805) vulnerability in Nvidia Triton Inference Server. Its CVSS base score is 8.1 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Privilege Escalation (T1068); ranked at the 50th 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 SA-11 (Developer Testing and Evaluation) and SA-15 (Development Process, Standards, and Tools) — 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-2025-23318 affects the Python backend in NVIDIA Triton Inference Server for Windows and Linux platforms. The vulnerability enables an out-of-bounds write condition, which could potentially result in code execution, denial of service, data tampering, and information disclosure. It has a CVSS v3.1 base score of 8.1 (AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H) and is linked to CWE-805 (Buffer Access with Incorrect Length Value) and CWE-787 (Out-of-bounds Write).

A remote network attacker with no privileges or user interaction required can exploit this vulnerability, though it demands high attack complexity. Successful exploitation grants high-impact confidentiality, integrity, and availability consequences, allowing arbitrary code execution, service disruption, data modification, or exposure of sensitive information on the targeted Triton Inference Server instance.

Mitigation guidance is available in official advisories, including the NVIDIA security bulletin at https://nvidia.custhelp.com/app/answers/detail/a_id/5687 and the NVD detail page at https://nvd.nist.gov/vuln/detail/CVE-2025-23318. Security practitioners should consult these for patch availability and recommended actions.

EU & UK References

Vulnerability Data

NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and…

more

information disclosure.

CWE(s)
CWE-805CWE-787

Related Threats

MITRE ATT&CK Enterprise Techniques

T1068 Exploitation for Privilege Escalation Privilege Escalation
Adversaries may exploit software vulnerabilities in an attempt to elevate privileges.
attack.mitre.org →
T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
attack.mitre.org →
T1203 Exploitation for Client Execution Execution
Adversaries may exploit software vulnerabilities in client applications to execute code.
attack.mitre.org →
T1210 Exploitation of Remote Services Lateral Movement
Adversaries may exploit remote services to gain unauthorized access to internal systems once inside of a network.
attack.mitre.org →
T1211 Exploitation for Stealth Stealth
Adversaries may exploit vulnerabilities to evade detection by hiding activity, suppressing logging, or operating within trusted or unmonitored components.
attack.mitre.org →
T1212 Exploitation for Credential Access Credential Access
Adversaries may exploit software vulnerabilities in an attempt to collect credentials.
attack.mitre.org →
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2025-23319Same product: Linux Linux Kernel
CVE-2024-0088Same product: Linux Linux Kernel
CVE-2026-53016Same product: Linux Linux Kernel
CVE-2026-31607Same product: Linux Linux Kernel
CVE-2023-0977Same product: Linux Linux Kernel
CVE-2023-0182Same product: Microsoft Windows
CVE-2023-0186Same product: Microsoft Windows
CVE-2024-49513Same product: Linux Linux Kernel
CVE-2023-35012Same product: Linux Linux Kernel
CVE-2023-0208Same product: Linux Linux Kernel

Affected Assets

nvidia
triton inference server
≤ 25.07

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

—

Detect
Catch it (NIST detect / respond)

—

Harden
Shrink the surface (DISA STIG)

—

Validate
Prove the fix (OWASP ASVS)
  • V1.4.1

Mitigating Controls (NIST 800-53 r5) AI

SA-11 Developer Testing and Evaluation good match

Developer testing and evaluation (including fuzzing and static analysis) directly finds incorrect length values used in sequential buffer accesses.

SA-15 Development Process, Standards, and Tools partial match

Requiring documented secure-development standards and tools can mandate bounds-checked coding practices that avoid the weakness.

SA-8 Security and Privacy Engineering Principles partial match

Secure engineering principles require explicit bounds checking and correct length calculations when performing buffer operations.

SI-10 Information Input Validation partial match

Input validation rejects or corrects malformed length values supplied from external sources before they reach buffer operations.

SI-16 Memory Protection partial match

Memory protection mechanisms limit the blast radius when an incorrect length value causes an out-of-bounds access.

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.

PR.PS-06 mostly match
prevents

Secure SDLC practices directly prevent incorrect-length buffer operations via safe APIs, reviews, and testing.

ID.RA-01 partial match
prevents

Vulnerability identification can discover buffer-length flaws but does not prevent their introduction.

PR.PS-02 partial match
prevents

Patching or replacing vulnerable software directly eliminates known instances of this coding weakness.

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.

A.8.29 Security testing in development and acceptance mostly match
finds

Security testing in development can detect out-of-bounds accesses, but does not guarantee prevention.

A.8.25 Secure development life cycle partial match
prevents

Secure development life cycle mandates buffer-safety practices that directly prevent incorrect length values.

A.8.26 Application security requirements partial match
prevents

Application security requirements can specify buffer-size validation, but do not prescribe implementation details.

A.8.27 Secure system architecture and engineering principles partial match
prevents

Secure architecture principles encourage bounds-checked APIs, yet leave concrete coding decisions to developers.

A.8.28 Secure coding partial match
prevents

Secure coding explicitly requires correct buffer-length handling, eliminating CWE-805 when followed.

A.8.32 Change management partial match
prevents

Change management can enforce review gates that catch unsafe memory operations before deployment.

References