CVE-2025-24357 vLLM allows a malicious model RCE by torch.load in hf_model_weights_iterator

What is CVE-2025-24357?

CVE-2025-24357 is a high-severity unsafe deserialization vulnerability in Vllm Vllm, published on 27 Jan 2025. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.

Official description

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: CWE-502

Which versions are affected by CVE-2025-24357?

3 open source packages ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2025-24357?

Upgrade vllm to 0.7.0 or later.

Upgrade, and only deserialise data from trusted sources or with an allow-list of types. More about Unsafe deserialization.

Is CVE-2025-24357 being exploited?

There is no known exploitation of CVE-2025-24357 in the wild and no public exploit code.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-rh4j-5rhw-hr54, PYSEC-2025-58.