Inference infrastructure

CVE-2026-24214 is a vulnerability in the DALI backend of NVIDIA Triton Inference Server, classified as CWE-190 (Integer Overflow or Wraparound). An attacker could trigger an integer overflow in that backend. A successful exploit might lead to code execution, data tampering, or denial of service.

NVIDIA Triton Inference Server contains an out-of-bounds read in its DALI backend, tracked as CVE-2026-24213 and classified under CWE-125. According to the source, a successful exploit might lead to code execution, data tampering, denial of service, or information disclosure. NVD has not yet provided an assessment, and the affected software versions are not listed in the source text.

NVIDIA Triton Inference Server contains an integer overflow vulnerability, classified as CWE-190 (Integer Overflow or Wraparound). An attacker could trigger it, and a successful exploit might lead to denial of service. NVD has not yet provided an assessment, and the record was published 05/20/2026.

NVIDIA Triton Inference Server contains a path traversal vulnerability, classified as CWE-22, that an attacker could trigger. The source states that a successful exploit might lead to denial of service. NVD has not yet provided an assessment, and the record was published on 05/20/2026.

NVIDIA Triton Inference Server contains an authentication bypass vulnerability, tracked as CVE-2026-24206 and classified under CWE-288 (Authentication Bypass Using an Alternate Path or Channel). The source states that a successful exploit might lead to privilege escalation, denial of service, or information disclosure. NVD had not yet provided an assessment at the time of publication.

Missing integrity verification in the Triton inference handler in Amazon SageMaker Python SDK v2 before v2.257.2 and v3 before v3.8.0 lets a remote authenticated actor with S3 write access to the model artifact path replace model artifacts with a crafted pickle payload. The payload is deserialized without verification, allowing code execution in inference containers.

CVE-2026-42249 affects Ollama for Windows. Its update mechanism passes values from attacker-controlled HTTP response headers directly to filepath.Join without validation, so ../ sequences let files be written outside the update staging directory, including the Windows Startup directory. Chained with CVE-2026-42248 (Missing Signature Verification for Updates), this yields automatic, persistent code execution without user awareness. Versions 0.12.10 to 0.17.5 were tested and confirmed vulnerable; other versions were not tested.

Ollama for Windows does not verify the integrity or authenticity of downloaded update executables. Its Windows update verification routine unconditionally returns success, so no digital signature or trust check runs before update payloads are staged or executed, letting attacker-supplied executables be accepted and run. Because updates install silently, a malicious payload may be installed without user awareness. Versions 0.12.10 to 0.17.5 were tested and confirmed vulnerable; other versions were not tested but might also be affected.

NVIDIA Triton Inference Server contains a vulnerability, CVE-2026-24175, classified as CWE-248 (Uncaught Exception). An attacker can crash the server by sending a malformed request header, which may lead to denial of service. NVD published the entry on 04/07/2026 and has not yet provided its own assessment.

CVE-2026-24174 affects NVIDIA Triton Inference Server. An attacker can crash the server by sending a malformed request, which might lead to denial of service. The weakness is classified as CWE-681, Incorrect Conversion between Numeric Types, and NVD has not yet provided an assessment.

NVIDIA Triton Inference Server contains a vulnerability, tracked as CVE-2026-24173, where an attacker can cause a server crash by sending a malformed request. The source states that a successful exploit might lead to denial of service. The weakness is classified as CWE-190, Integer Overflow or Wraparound, and NVD published the entry on 04/07/2026.