CVE-2025-23331
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability where a user could cause a memory allocation with excessive size value, leading to a segmentation fault, by providing an invalid request. A successful exploit of this vulnerability might lead to denial of service.
Scoring
- Severity
- HIGH
- CVSS base score
- 7.5
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- EPSS probability
- 0.56%
- CWE
- CWE-789
- Published
- 2025-08-06
- Last modified
- 2026-03-13
Affected products
- NVIDIA Triton Inference Server
Weakness type
Related vulnerabilities
- CVE-2026-83530 — Uncontrolled Memory Allocation in cel-go
- CVE-2026-86776 — KeePass 2.35 through 2.61.1 Memory Exhaustion via KDBX Header Field Size
- CVE-2026-19204 — A client may send a WebSocket frame with an unknown opcode and a very large declared payload...
- CVE-2026-85201 — In Eclipse Ankaios versions 0.1.0 through 1.0.1, the agent does not limit the length declared by a...
- CVE-2026-85445 — MOOS-IvP through 24.8.1 BHV_IPF Demultiplexer Memory Exhaustion via Packet Count
- CVE-2026-85442 — MOOS core-moos through 10.4.0 MOOSDB Denial of Service via Unbounded Packet Allocation
- CVE-2026-84888 — RightNow-AI OpenFang tool_runner.rs shell_exec memory allocation
- CVE-2026-84857 — sigoden aichat API Endpoint serve.rs memory allocation