CVE-2026-28500
HighCVSS 8.6Exploitation Probability (EPSS)
Low risk24th percentile - higher than 24% of all known CVEs
Summary
In ONNX library versions up to 1.20.1, a security control bypass exists in onnx.hub.load() due to improper logic in repository trust verification. Using the silent=True parameter suppresses all security warnings, enabling zero-interaction supply-chain attacks.
Risk Assessment
The risk involves supply-chain attacks where loading a malicious model can silently exfiltrate sensitive files like SSH keys or cloud credentials from the victim's machine without user interaction.
Recommendation
Immediately stop using onnx.hub.load() with the silent=True parameter and monitor official channels for patches. Until a fix is available, avoid loading models from untrusted sources.
Other vulnerabilities in ONNX
See all- CVE-2026-49114High
ONNX before version 1.21.0 contains a vulnerability in the 'save_external_data' function that builds the external-data file path and opens it for writing without O_NOFOLLOW/O_EXCL, after a non-atomic 'os.path.isfile()' check. A local attacker can pre-plant a symlink, causing the victim's write to append to any file the victim can write.
- CVE-2026-63632Low
A vulnerability in the ONNX library from version 1.3.0 to 1.22.0 allows an out-of-bounds read in Gemm_7_6::adapt_gemm_7_6() during opset 7 to 6 downgrade when a Gemm node has input tensors with fewer than two dimensions. This can cause a process crash.
- CVE-2026-44512Medium
A vulnerability in the ONNX library (versions 1.9.0 through 1.22.0) allows a null pointer dereference in the Upsample_6_7::adapt_upsample_6_7() function when processing a malicious model with an Upsample node having zero inputs. This leads to an unrecoverable denial of service (DoS).
- CVE-2026-27489High
A path traversal vulnerability via symlink was found in the ONNX library before version 1.21.0. It allows reading arbitrary files outside the model or user-provided directory.
Original NVD description (English source)
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. In versions up to and including 1.20.1, a security control bypass exists in onnx.hub.load() due to improper logic in the repository trust verification mechanism. While the function is designed to warn users when loading models from non-official sources, the use of the silent=True parameter completely suppresses all security warnings and confirmation prompts. This vulnerability transforms a standard model-loading function into a vector for Zero-Interaction Supply-Chain Attacks. When chained with file-system vulnerabilities, an attacker can silently exfiltrate sensitive files (SSH keys, cloud credentials) from the victim's machine the moment the model is loaded. As of time of publication, no known patched versions are available.