{"action":"Upgrade vllm to 0.7.0 or later.","affected":[{"fixed":"0.7.0","introduced":"0"}],"component":"vllm","cve_ids":["CVE-2025-24357"],"ecosystem":"PyPI","epss":0.00868,"exploited":false,"fixed_versions":["0.7.0"],"ghsa_id":"GHSA-rh4j-5rhw-hr54","id":"tcs_01M5KGPRSTZ91NS6MRMYN0693S","modified_at":"2025-06-27T21:56:54.188774Z","published_at":"2025-01-27T18:15:41Z","references":["https://osv.dev/vulnerability/PYSEC-2025-58","https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54","https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04","https://github.com/vllm-project/vllm/pull/12366","https://pytorch.org/docs/stable/generated/torch.load.html"],"severity":{"label":"high","score":8.8},"sources":[{"source":"osv","source_id":"PYSEC-2025-58","url":"https://osv.dev/vulnerability/PYSEC-2025-58"}],"summary":"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 th"}