Project-Onyx

Project Onyx Advanced EDR Evasion via AI Telemetry Spoofing & WASM Sandboxing. Project Onyx is a PoC Red Team pipeline designed to demonstrate advanced evasion techniques against modern EDR systems. It shifts away from traditional signature-based obfuscation towards behavioral camouflage and stri...

PROMPTPurify

promptpurify Tiny prompt-injection firewall for LLM chat apps. 14 MB. CPU-only. Drop-in guard between your user input and your LLM — runs on the same box, no GPU, no API, no extra service. Built by the SecureLayer7 red-team. Most OSS guardrails are hundreds of MB, want a GPU, and still miss the...

Cawdog

CAWODOG – IP Protection PoC for Python-Based Industrial AI CAWODOG Cat World Dominance Group is a playful but realistic proof-of-concept for protecting Python-based AI models deployed on offline industrial machines. The core idea: Take a small image classifier that detects dogs the “enemy” of...

CVE-2026-19319

The IBM Watson Speech Services Cartridge versions 4.0.0 through 5.4.0 are vulnerable to an out-of-bounds read in the Onnx component. The root cause is a flaw in the adapt_gemm_7_6 function when processing specific input, which could allow a remote attacker to obtain sensitive information. This vu...

ONNX: Denial Of Service Via Unchecked Expansion Of Packed Sub-byte Tensors In ONNX Python APIs

Summary ONNX's Python tensor-materialization helpers could allocate memory according to attacker-controlled tensor dimensions without verifying that a packed sub-byte payload contained the declared number of elements. A very small model could therefore cause a disproportionately large allocation...

ONNX: Null Pointer Dereference In ScanInferenceFunction Due To Missing Required Attribute

Summary ONNX shape inference did not safely validate the required Scan "numscaninputs" attribute. Two malformed values could terminate or disrupt the process: 1. If the attribute was missing, "ctx.getAttribute"numscaninputs"" returned null and was dereferenced. 2. If the attribute was negative,...

ONNX: Out-of-bounds Read In ConvTranspose Shape Inference Via Undersized Weight Rank

Summary ONNX ConvTranspose shape inference performed an out-of-bounds read when the weight tensor had fewer than three dimensions and the model did not provide a "kernelshape" attribute. The inference function derived an empty "effectivekernelshape" vector from the undersized weight tensor, then...

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

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. "RNNShapeInferenceopset1to6" checked whether the input shape was present but accessed "dim0" and "dim1" without first...

EUVD-2026-110041

ONNX: Out-of-bounds read in ConvTranspose shape inference via undersized weight rank...

ONNX: Out-of-bounds read in ConvTranspose shape inference via undersized weight rank

Summary ONNX ConvTranspose shape inference performed an out-of-bounds read when the weight tensor had fewer than three dimensions and the model did not provide a kernelshape attribute. The inference function derived an empty effectivekernelshape vector from the undersized weight tensor, then...

acetone-nnet (>=0.1.0.dev2, <=0.4.0.dev1), acuity (6.18.0) +525 more potentially affected by CVE-2026-115920 via onnx (>=1.2.1, <=1.21.0)

onnx PYPI version =1.2.1, =0.1.0.dev2, =6.6.0, =0.3.0, =0.1.0, =2.0.0, =0.0.0, =1.0.1, =0.0.8, =0.1.0, =0.5.0 and more Source cves: CVE-2026-115920 Source advisory: GHSA-6PWM-X34P-FVJ2...

GHSA-6PWM-X34P-FVJ2 ONNX: Out-of-bounds read in ConvTranspose shape inference via undersized weight rank

Summary ONNX ConvTranspose shape inference performed an out-of-bounds read when the weight tensor had fewer than three dimensions and the model did not provide a kernelshape attribute. The inference function derived an empty effectivekernelshape vector from the undersized weight tensor, then...

acetone-nnet (>=0.1.0.dev2, <=0.4.0.dev1), acuity (6.18.0) +525 more potentially affected by CVE-2026-115920 via onnx (>=1.2.1, <=1.21.0)

onnx PYPI version =1.2.1, =0.1.0.dev2, =6.6.0, =0.3.0, =0.1.0, =2.0.0, =0.0.0, =1.0.1, =0.0.8, =0.1.0, =0.5.0 and more Source cves: CVE-2026-115920 Source advisory: OSV:GHSA-6PWM-X34P-FVJ2...

onnx-tf (>=0.1.0, <=0.1.1) potentially affected by CVE-2026-115922 via onnx (0.2.0)

onnx PYPI version 0.2.0 is affected by a known vulnerability. The following packages have a transitive dependency on onnx and may be impacted: - onnx-tf =0.1.0, =0.1.1 Source cves: CVE-2026-115922 Source advisory: OSV:GHSA-Q69G-F4F5-V8M7...

acetone-nnet (>=0.1.0.dev2, <=0.4.0.dev1), acuity (6.18.0) +525 more potentially affected by CVE-2026-115922 via onnx (>=1.1.1, <=1.21.0)

onnx PYPI version =1.1.1, =0.1.0.dev2, =6.6.0, =0.3.0, =0.1.0, =2.0.0, =0.0.0, =1.0.1, =0.0.8, =0.1.0, =0.5.0 and more Source cves: CVE-2026-115922 Source advisory: GHSA-Q69G-F4F5-V8M7...

EUVD-2026-110049

ONNX: Denial of service via unchecked expansion of packed sub-byte tensors in ONNX Python APIs...

acetone-nnet (>=0.1.0.dev2, <=0.4.0.dev1), acuity (6.18.0) +525 more potentially affected by CVE-2026-115922 via onnx (>=1.1.1, <=1.21.0)

onnx PYPI version =1.1.1, =0.1.0.dev2, =6.6.0, =0.3.0, =0.1.0, =2.0.0, =0.0.0, =1.0.1, =0.0.8, =0.1.0, =0.5.0 and more Source cves: CVE-2026-115922 Source advisory: OSV:GHSA-Q69G-F4F5-V8M7...

ONNX: Denial of service via unchecked expansion of packed sub-byte tensors in ONNX Python APIs

Summary ONNX's Python tensor-materialization helpers could allocate memory according to attacker-controlled tensor dimensions without verifying that a packed sub-byte payload contained the declared number of elements. A very small model could therefore cause a disproportionately large allocation...

GHSA-Q69G-F4F5-V8M7 ONNX: Denial of service via unchecked expansion of packed sub-byte tensors in ONNX Python APIs

Summary ONNX's Python tensor-materialization helpers could allocate memory according to attacker-controlled tensor dimensions without verifying that a packed sub-byte payload contained the declared number of elements. A very small model could therefore cause a disproportionately large allocation...

acetone-nnet (>=0.1.0.dev2, <=0.4.0.dev1), acuity (6.18.0) +523 more potentially affected by CVE-2026-115921 via onnx (>=1.4.1, <=1.21.0)

onnx PYPI version =1.4.1, =0.1.0.dev2, =6.6.0, =0.3.0, =0.1.0, =2.0.0, =0.0.0, =1.0.1, =0.0.8, =0.1.0, =0.5.0 and more Source cves: CVE-2026-115921 Source advisory: OSV:GHSA-M4PR-6V3C-6FGR...