KEVWire

Security intelligence, with context.

Response snapshot Oct 29, 2026, 02:31 UTC

Back to the wire
Permalink
VulnerabilityCVE-2026-115919

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

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.

Published Updated

At a glance

Exploited
Not known
Severity
6.2 Medium (CVSS 3.1)
Chance of exploitation
0.2% in the next 30 days
Sources
1 source

What to do

GitHub lists first patched versions: onnx: 1.22.0. Confirm the affected range and upgrade guidance in the exact advisory.

Read GitHub-reviewed advisory GHSA-48m4-24cq-37qf (opens a new tab)

What happened

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

Continue reading

The vulnerable code read dimensions unconditionally:

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 14+ inference paths already required the first input to have rank three and were not affected.

Impact

An application that performs shape inference on an untrusted model can be terminated, causing denial of service. Exploitation does not require privileges or human interaction once the model is processed. No confidentiality or integrity impact was demonstrated.

Affected versions

- Affected: ONNX through 1.21.0 - Patched: ONNX 1.22.0

The vulnerable schemas are limited to RNN and LSTM opsets 1–6 and GRU opsets 3–6.

Remediation

Upgrade to ONNX 1.22.0 or later. The fix validates that the first input has rank three before accessing its dimensions.

- Fix: [onnx/onnx#7879](https://github.com/onnx/onnx/pull/7879) - Commit: [92e541266](https://github.com/onnx/onnx/commit/92e541266af5dd38cfa48aeb92206f4268a066cd)

The original malformed model was also re-tested against the published ONNX 1.23.2 wheel and correctly raises InferenceError.

Severity

The vulnerable ONNX component processes the malicious model through a local library API or file boundary and is not itself bound to a network stack. Applications that expose ONNX model processing over a network should calculate an Environmental score with Modified Attack Vector set to Network.

Affected package ranges reported by GitHub: onnx: <= 1.21.0

Scores and how they were measured

CVSS base severity

6.2

Version 3.1As of

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

Measurement source (opens a new tab)

How bad it is if exploited. Not a prediction of exploitation or proof you are exposed.

EPSS probability

0.2%

Scored Percentile 7.4%

Model and measurement source (opens a new tab)

A model's estimate of exploitation in the next 30 days, not certainty or your own risk.

Related technology

Follow Python packages (PyPI): RSS feedAll its recordsAsk your AI assistant

Sources

  1. Primary source

    GitHub-reviewed advisory GHSA-48m4-24cq-37qf (opens a new tab)

    The public advisory supplies the description, affected package/version ranges, and any listed CVSS metric. GitHub review is not local review.

    Published Checked

  2. Primary source

    GitHub public advisory API page (opens a new tab)

    The API page supplied GHSA-48m4-24cq-37qf, its actual identifiers, source dates, and structured metrics.

    Published Date not suppliedChecked

  3. Primary source

    FIRST measured EPSS score (opens a new tab)

    Measured EPSS probability and percentile for CVE-2026-115919, scored 2026-10-28. This is a model estimate, not proof of exposure.

    Published Checked

Cite this record

For factual claims, cite the primary sources above; cite KEVWire for its compilation, dates, and classifications.

APA

KEVWire. (2026, October 28). ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check) (CVE-2026-115919). https://kevwire.com/record/CVE-2026-115919

MLA

"ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check) (CVE-2026-115919)." KEVWire, 28 Oct. 2026, kevwire.com/record/CVE-2026-115919.

Chicago

KEVWire. "ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check) (CVE-2026-115919)." Last modified October 28, 2026. https://kevwire.com/record/CVE-2026-115919.

Evidence summary (plain text)

ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check) (Oct 28, 2026).
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.
CVSS 6.2 (version 3.1; evidence as of Oct 28, 2026; https://github.com/advisories/GHSA-48m4-24cq-37qf).
EPSS 0.2% for the following 30 days, scored Oct 28, 2026 (https://api.first.org/data/v1/epss?cve=CVE-2026-115919&date=2026-10-28).
Sources:
GitHub-reviewed advisory GHSA-48m4-24cq-37qf: https://github.com/advisories/GHSA-48m4-24cq-37qf
GitHub public advisory API page: https://api.github.com/advisories?type=reviewed&per_page=100&sort=updated&direction=desc
FIRST measured EPSS score: https://api.first.org/data/v1/epss?cve=CVE-2026-115919&date=2026-10-28
Record ID: CVE-2026-115919.
Record origin: Ingested record.
AI evidence: Not assessed.
Known exploitation: Not assessed.
Zero-day status: Not assessed. KEV membership alone does not establish zero-day status.
About this data

This record was ingested from a data source. Retrieved: Oct 29, 2026, 02:16 UTC. Ingestion is not an independent editorial investigation.

A CISA KEV listing documents known exploitation, not necessarily a zero-day; absence from the catalog does not prove a vulnerability has never been exploited.

Technology tags indicate possible relevance, not verified exposure. Confirm the affected product, version, and configuration against your own inventory; KEVWire does not scan your systems.

A personal reading checklist on this device, not verified remediation.

Record JSON

Your account

Email alerts

Email alerts are coming as part of KEVWire Premium: join the waitlist. To follow your stack today, use its RSS feed, which honors your filters, or connect an AI agent through the API.

Suggest an improvement

Ideas, missing sources, corrections, and bugs are all welcome. No account needed. Suggestions are reviewed by a person before anything changes.

Record details

Record detail