{"id":"CVE-2025-24357","aliases":["GHSA-rh4j-5rhw-hr54","PYSEC-2025-58"],"url":"https://o3.security/vulnerability/CVE-2025-24357","summary":"vLLM allows a malicious model RCE by torch.load in hf_model_weights_iterator","details":"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.","published":"2025-01-27T17:38:20.070Z","modified":"2026-08-08T03:47:52.473591851Z","cvss":{"score":7.5,"severity":"HIGH","vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H"},"epss":null,"cisaKev":null,"exploitsKnown":0,"affectedPackages":[{"ecosystem":"PyPI","name":"vllm","fixedVersion":"0.7.0"}],"fix":{"url":"https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04","label":"vllm-project/vllm@d3d6bb1"},"references":[{"type":"WEB","url":"https://pytorch.org/docs/stable/generated/torch.load.html"},{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/24xxx/CVE-2025-24357.json"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2025-24357"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/pull/12366"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-08-08T03:47:52.473591851Z"}}