{"items":[{"id":"NVI-00008954","kind":"vulnerability","title":"ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check)","revision":2,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-48m4-24cq-37qf","CVE-2026-115919"],"plain_summary":"GitHub lists this reviewed advisory for onnx. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-006e5cbcb657fc04c8ca5885117689e4"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-10-28T21:16:24.000Z","value":"6.2 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-4905b62ebc3a391a867d2667dda6493c"},{"kind":"EPSS","as_of":"2026-11-02T12:00:30.000Z","value":"0.178%","meaning":"FIRST EPSS model v2026.06.15; exploitation probability over 30 days, percentile 0.07407. Missing scores are unknown.","source_id":"sr-006e5cbcb657fc04c8ca5885117689e4"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-4905b62ebc3a391a867d2667dda6493c","url":"https://github.com/advisories/GHSA-48m4-24cq-37qf","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-48m4-24cq-37qf","publisher":"GitHub Advisory Database","observed_at":"2026-10-31T21:56:08.420Z"},{"id":"sr-006e5cbcb657fc04c8ca5885117689e4","url":"https://www.first.org/epss/data.html","basis":"official_catalog","notes":"FIRST EPSS; probability of exploitation in the next 30 days, not local compromise. Dataset date/model retained; FIRST services terms apply.","title":"CVE-2026-115919","publisher":"FIRST EPSS","observed_at":"2026-11-02T20:15:58.842Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-4905b62ebc3a391a867d2667dda6493c"],"technology":"onnx","known_exclusions":[],"conditions_summary":"## Summary\n\nONNX 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.\n\n`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.\n\n## Technical details\n\nThe vulnerable code read dimensions unconditionally:\n\n```cpp\nif (hasInputShape(ctx, 0)) {\n  const auto& first_input_shape = getInputShape(ctx, 0);\n  seq_length = first_input_shape.dim(0);\n  batch_size = first_input_shape.dim(1);\n}\n```\n\nFor 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.\n\nThe newer opset 7–13 and opset 14+ inference paths already required the first input to have rank three and were not affected.\n\n## Impact\n\nAn application that performs shape inference on an untrusted model can be terminat","public_affected_ranges":["<= 1.21.0"]}],"null_published_at":"2026-11-03T17:49:14.967Z","source_updated_at":"2026-10-28T21:16:24.000Z","source_disclosed_at":"2026-10-28T21:16:24.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"Dated EPSS estimate updated; this is not a new disclosure or proof of exploitation.","null_first_observed_at":"2026-10-31T21:56:08.420Z"},{"id":"NVI-00008954","kind":"vulnerability","title":"ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check)","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-48m4-24cq-37qf","CVE-2026-115919"],"plain_summary":"GitHub lists this reviewed advisory for onnx. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-4905b62ebc3a391a867d2667dda6493c"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-10-28T21:16:24.000Z","value":"6.2 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-4905b62ebc3a391a867d2667dda6493c"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-4905b62ebc3a391a867d2667dda6493c","url":"https://github.com/advisories/GHSA-48m4-24cq-37qf","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-48m4-24cq-37qf","publisher":"GitHub Advisory Database","observed_at":"2026-10-31T21:56:08.420Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-4905b62ebc3a391a867d2667dda6493c"],"technology":"onnx","known_exclusions":[],"conditions_summary":"## Summary\n\nONNX 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.\n\n`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.\n\n## Technical details\n\nThe vulnerable code read dimensions unconditionally:\n\n```cpp\nif (hasInputShape(ctx, 0)) {\n  const auto& first_input_shape = getInputShape(ctx, 0);\n  seq_length = first_input_shape.dim(0);\n  batch_size = first_input_shape.dim(1);\n}\n```\n\nFor 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.\n\nThe newer opset 7–13 and opset 14+ inference paths already required the first input to have rank three and were not affected.\n\n## Impact\n\nAn application that performs shape inference on an untrusted model can be terminat","public_affected_ranges":["<= 1.21.0"]}],"null_published_at":"2026-10-31T22:13:27.124Z","source_updated_at":"2026-10-28T21:16:24.000Z","source_disclosed_at":"2026-10-28T21:16:24.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-10-31T21:56:08.420Z"}],"next_cursor":null,"snapshot_revision":"42594"}