CVE-2025-24357

vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in v0.7.0.

Weakness

The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.

Affected Software

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

• https://cwe.mitre.org/data/definitions/586.html

References

• https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04
• https://github.com/vllm-project/vllm/pull/12366
• https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54
• https://pytorch.org/docs/stable/generated/torch.load.html