Ray prior to 2.56.0 contains an unsafe deserialization vulnerability in the WebDataset reader that allows attackers to achieve remote code execution by supplying a malicious tar archive to the read_webdataset() function. The _default_decoder() function in webdataset_datasource.py unconditionally calls pickle.loads() on tar entries with .pkl/.pickle extensions and torch.load() with weights_only=False on .pt/.pth entries, executing arbitrary code inside Ray remote workers on every worker that processes the malicious archive.
Weakness
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
Affected Software
| Name | Vendor | Start Version | End Version |
|---|---|---|---|
| Ray | Anyscale | * | 2.56.0 (excluding) |
Potential Mitigations
- Make fields transient to protect them from deserialization.
- An attempt to serialize and then deserialize a class containing transient fields will result in NULLs where the transient data should be. This is an excellent way to prevent time, environment-based, or sensitive variables from being carried over and used improperly.
Related Attack Patterns
References
- https://github.com/ray-project/ray/pull/63469
- https://github.com/ray-project/ray/pull/63470
- https://github.com/ray-project/ray/releases/tag/ray-2.56.0
- https://github.com/ray-project/ray/security/advisories/GHSA-hhrp-gw25-jr43
- https://www.vulncheck.com/advisories/ray-unsafe-deserialization-rce-via-webdataset-reader
- https://github.com/ray-project/ray/security/advisories/GHSA-hhrp-gw25-jr43