FYI - ONNX will automatically exfiltrate data about your application with no way to opt out other than building it from source with telemetry disabled. Maybe you could block DNS too.
Aren't there other ONNX runtimes out there? A quick google search shows a few written in Rust: Tract, RTen, WONNX, Burn&Candle. Also, IIRC there's a Julia-based one as well.
> The ONNX Runtime (ORT) is the most widely used engine for serving deep
learning models in production. It is common for people to download ONNX
models from public repositories, such as Hugging Face, and to serve them to
their customers without too much scrutiny. In March 2026, we noticed a
parser flaw: an ONNX model can cause ORT to read from arbitrary file paths
(or memory addresses) without validations.
We found out about this this morning, when evals started failing in our pipelines. I've been looking around, but it doesn't seem like there was any advance warning about this.
Does anyone know why or how a repository with 22k stars just went dark?
If I understand your implication, that's not what "supply chain attack" normally means. That term means attacking the mechanism that delivers your packages to deliver a different, more compromised, package. If the package itself is already compromised then that's just a straightforward dependency vulnerability.
That would be my guess also. About 6 months ago the azure-functions-host repo disappeared for a while (I got a concerning automated email from GitHub from my forked repo citing a ToS violation).
The closest/furthest ahead fork I could find is https://github.com/intel/onnxruntime for anyone else needing it, though that's with Intel's OpenVINO modifications
Maybe related to one of their packages that was compromised? Not sure if GitHub was the attack vector, but possibly tidying stuff up
Source: https://opensourcemalware.com/blog/agent-framework-pypi-comp...
FYI - ONNX will automatically exfiltrate data about your application with no way to opt out other than building it from source with telemetry disabled. Maybe you could block DNS too.
Aren't there other ONNX runtimes out there? A quick google search shows a few written in Rust: Tract, RTen, WONNX, Burn&Candle. Also, IIRC there's a Julia-based one as well.
https://github.com/tracel-ai/burn-onnx
I maintain this project at the moment.
It convert ONNX models into native, backend-agnostic Burn code for inference and fine-tuning.
I wonder if they found new vectors that backdoor'ed models could exploit, like that discussed in the most recent Phrack [^0]
[0]: https://phrack.org/issues/73/backdoor-attacks-against-machin...
> The ONNX Runtime (ORT) is the most widely used engine for serving deep learning models in production. It is common for people to download ONNX models from public repositories, such as Hugging Face, and to serve them to their customers without too much scrutiny. In March 2026, we noticed a parser flaw: an ONNX model can cause ORT to read from arbitrary file paths (or memory addresses) without validations.
That's why I am running pretty much all tools written in almost any language (Python, TS/JS, Ruby, Rust, and Go) in a sandbox now.
Almost everything seems exploitable, and a sandbox adds at least one more layer of protection against those attacks.
https://github.com/ashishb/amazing-sandbox
We found out about this this morning, when evals started failing in our pipelines. I've been looking around, but it doesn't seem like there was any advance warning about this.
Does anyone know why or how a repository with 22k stars just went dark?
Probably being used in supply chains, and got attacked.
If I understand your implication, that's not what "supply chain attack" normally means. That term means attacking the mechanism that delivers your packages to deliver a different, more compromised, package. If the package itself is already compromised then that's just a straightforward dependency vulnerability.
That would be my guess also. About 6 months ago the azure-functions-host repo disappeared for a while (I got a concerning automated email from GitHub from my forked repo citing a ToS violation).
Why do you think star amount has anything to do with ability to go dark?
it's called "Open Neural Network Exchange (ONNX)", perhaps microsoft is taking a page from OpenAI on what open meanings.
The closest/furthest ahead fork I could find is https://github.com/intel/onnxruntime for anyone else needing it, though that's with Intel's OpenVINO modifications
This is why we vendor everything.
You never know when it's going to vanish
If it were me, I would take the hint and maybe not trust a vendored version right now?
https://github.com/syntax-syndicate/onnxruntime
For others:
> https://github.com/syntax-syndicate/onnxruntime
Check the web archive link for commit hashes, the syntax-syndicate fork seems to be the remaining legit fork.
[1] https://web.archive.org/web/20261113082932/https://github.co...
It's here: https://github.com/onnx/onnx
This is not the same package.
omg, I just built something depending on this. Hopefully the web version is still cached in NPM.
Very concerning!
Maybe related to the recent release of MAI? Or the Microsoft AI models?
Someone with a copy should soft fork it