Summary
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.
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:
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.
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.
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.
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.
A read operation accesses a memory location beyond the intended buffer boundary. Typical impact: sensitive data disclosure or crash.
CVE-2026-115919 has a CVSS score of 6.2 (Medium). The vector is requires local access, no privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (1.22.0); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
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
- Commit:
92e541266
The original malformed model was also re-tested against the published ONNX 1.23.2 wheel and correctly raises InferenceError.
Frequently Asked Questions
- What is CVE-2026-115919? CVE-2026-115919 is a medium-severity out-of-bounds read vulnerability in onnx (pip), affecting versions <= 1.21.0. It is fixed in 1.22.0. A read operation accesses a memory location beyond the intended buffer boundary.
- How severe is CVE-2026-115919? CVE-2026-115919 has a CVSS score of 6.2 (Medium). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which versions of onnx are affected by CVE-2026-115919? onnx (pip) versions <= 1.21.0 is affected.
- Is there a fix for CVE-2026-115919? Yes. CVE-2026-115919 is fixed in 1.22.0. Upgrade to this version or later.
- Is CVE-2026-115919 exploitable, and should I be worried? Whether CVE-2026-115919 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-115919 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-115919? Upgrade
onnxto 1.22.0 or later.