ONNX Runtime is a performance-focused inference engine for ONNX (Open Neural Network Exchange) models.
94%
Total Score
100
100
90
100
Thirteen analyzed workflows lack top-level permissions and 16 declare top-level write access, which is a workflow-hardening gap; however, the dangerous-workflow scan found no high-risk trigger, checkout, or injection pattern.
| Title | Versions | Severity |
|---|---|---|
AIKIDO-2026-10294 Pre-CVE Found by Aikido Intel before public disclosure or CVE publication. onnxruntime is vulnerable to Out-of-bound read in versions 0.1.4 - 1.24.1. | 0.1.4 - 1.24.1 | Medium |
AIKIDO-2026-10184 Pre-CVE Found by Aikido Intel before public disclosure or CVE publication. onnxruntime is vulnerable to Null Pointer Dereference in versions 1.23.0 - 1.24.0. | 1.23.0 - 1.24.0 | Medium |
No maintainer information available.
No direct dependencies.
Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.
Free. No credit card required.

I consent to receiving marketing communications based on Aikido’s Privacy Policy.
SOC 2Compliant
ISO 27001Compliant
ISO 42001Compliant© All Intel data is openly available and commercially licensed.