• hiddenvulkcan 44 minutes ago

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...

• eddythompson80 15 minutes ago

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.

• UncleOxidant 15 minutes ago

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.

• antimora 8 minutes ago

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.

• spdustin an hour ago

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...

• momojo 41 minutes ago

> 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.

• ashishb 26 minutes ago

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

• nvader 2 hours ago

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?

• FesterCluck 2 hours ago

Probably being used in supply chains, and got attacked.

• quietbritishjim 30 minutes ago

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.

• robjam an hour ago

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).

• Neywiny 2 hours ago

Why do you think star amount has anything to do with ability to go dark?

• binsquare 2 hours ago

it's called "Open Neural Network Exchange (ONNX)", perhaps microsoft is taking a page from OpenAI on what open meanings.

• Heliodex an hour ago

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

• dangoodmanUT 35 minutes ago

This is why we vendor everything.

You never know when it's going to vanish

• KirinDave 29 minutes ago

If it were me, I would take the hint and maybe not trust a vendored version right now?

• tokyovigilante 23 minutes ago
• cookiengineer a minute ago

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...

• gtirloni an hour ago
• russdill an hour ago

This is not the same package.

• proc0 26 minutes ago

omg, I just built something depending on this. Hopefully the web version is still cached in NPM.

• tomrod an hour ago

Very concerning!

• Axodouble an hour ago

Maybe related to the recent release of MAI? Or the Microsoft AI models?

• matt3210 an hour ago

Someone with a copy should soft fork it