[GHSA-hj95-mhgf-jxc4] ExecuTorch integer overflow vulnerability #6255
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Updates
Comments
I was looking into the 6 recent executorch overflow vulns, and the implementation of executorch, and noticed that loading models can be performed in the runtime APIs as well as in Python. Here are the docs to show what I mean: https://docs.pytorch.org/executorch/stable/getting-started.html#running-on-device
I think we should also list these runtime API packages as affected products.
Android (Java/Kotlin): https://github.com/pytorch/executorch/blob/b021fd01eab33b14749197a1fd7bbd2dfa85e823/extension/android/README.md, https://mvnrepository.com/artifact/org.pytorch/executorch-android
iOS (Objective-C and Swift): https://github.com/pytorch/executorch/blob/main/Package.swift#L129, https://swiftpackageindex.com/pytorch/executorch
C++: N/A, no package manager