vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator
### Description The vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It use torch.load function and weights_only parameter is default value False. There is a security warning on https://pytorch.org/docs/stable/generated/torch.load.html, when torch.load load a malicious pickle data it will execute arbitrary code during unpickling. ### Impact This vulnerability can be exploited to execute arbitrary codes and OS commands in the victim machine who fetch the pretrained repo remotely. Note that most models now use the safetensors format, which is not vulnerable to this issue. ### References * https://pytorch.org/docs/stable/generated/torch.load.html * Fix: https://github.com/vllm-project/vllm/pull/12366
beschreibt (1)
Zugehörige CVEs.
| ID | Schweregrad | ausnutzbar | ||
|---|---|---|---|---|
| CVE-2025-24357US | high8.8 | — | ||
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 hug… | ||||
Referenzen
Externe Belege — Patches, Meldungen, Analysen.
- https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-58.yamlWEB
- https://github.com/vllm-project/vllmPACKAGE
- https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04WEB
- https://github.com/vllm-project/vllm/pull/12366WEB
- https://github.com/vllm-project/vllm/releases/tag/v0.7.0WEB
- https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54WEB
- https://nvd.nist.gov/vuln/detail/CVE-2025-24357ADVISORY
- https://pytorch.org/docs/stable/generated/torch.load.htmlWEB
Advisories wie diese benennen die exponierten Produkte, die Angreifer auf Ihrer Angriffsfläche ins Visier nehmen. Sehen Sie mit einem kostenlosen Passiv-Scan, was exponiert ist.
Kostenloser Scan