ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check)

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

6.2 · CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

EPSS

• CVE-2026-115919: 0.18% estimated exploitation activity in the next 30 days; percentile 7.46 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary ONNX shape inference performed an out-of-bounds read when processing a malformed RNN, GRU, or LSTM node from opsets 1–6 whose first input had a rank other than three. `RNNShapeInference_opset1_to_6()` checked whether the input shape was present but accessed `dim(0)` and `dim(1)` without first checking its rank. A crafted model could therefore terminate a process that called `onnx.shape_inference.infer_shapes()`. The model passed `onnx.checker.check_model()` before reaching the vulnerable path.

Technical details The vulnerable code read dimensions unconditionally: ```cpp if (hasInputShape(ctx, 0)) { const auto& first_input_shape = getInputShape(ctx, 0); seq_length = first_input_shape.dim(0); batch_size = first_input_shape.dim(1); } ``` For an undersized shape, protobuf's repeated-field access read outside the intended array in release builds. The observed result was SIGSEGV; sanitizer and debug builds terminated on a protobuf bounds check. The newer opset 7–13 and opset…

Published by the source

28 Oct 2026, 21:16 UTC

Last modified by the source

28 Oct 2026, 21:30 UTC

Source last checked

29 Oct 2026, 06:10 UTC

1. Revision 2 · amended · 29 Oct 2026

   Amended from osv record GHSA-48m4-24cq-37qf

2. Revision 1 · created · 28 Oct 2026

   Published from ghsa record GHSA-48m4-24cq-37qf

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-115919

Advisory: ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check)
IDs: CVE-2026-115919, GHSA-48m4-24cq-37qf
Record: https://patchnext.com/advisories/cve-2026-115919 (revision 2, source checked 29 Oct 2026, 06:10 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 6.2)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: onnx 1.22.0. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI onnx: affected < 1.22.0; fixed in 1.22.0

## Suggested inspection (read-only)
- `python -m pip show onnx`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on onnx.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-48m4-24cq-37qf (OSV record GHSA-48m4-24cq-37qf lists affected ranges: PyPI onnx >=0 <1.22.0 (fixed))
- Verified: https://github.com/advisories/GHSA-48m4-24cq-37qf (GitHub-reviewed advisory GHSA-48m4-24cq-37qf lists affected ranges: PyPI onnx >=0 <=1.21.0)

Commands are suggestions: review each one before running it.