Ce mail provient de l'extérieur, restons vigilants ===================================================================== CERT-Renater Note d'Information No. 2025/VULN044 _____________________________________________________________________ DATE : 28/01/2025 HARDWARE PLATFORM(S): / OPERATING SYSTEM(S): Systems running vllm versions prior to 0.7.0. ===================================================================== https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 _____________________________________________________________________ Malicious model to RCE by torch.load in hf_model_weights_iterator High russellb published GHSA-rh4j-5rhw-hr54 Jan 27, 2025 Package vllm (pip) Affected versions <= 0.7.0 Patched versions v0.7.0 Description 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: #12366 Severity High 7.5/ 10 CVSS v3 base metrics Attack vector Network Attack complexity High Privileges required None User interaction Required Scope Unchanged Confidentiality High Integrity High Availability High CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H CVE ID CVE-2025-24357 Weaknesses CWE-502 Credits @DogeWatch DogeWatch Reporter ========================================================= + CERT-RENATER | tel : 01-53-94-20-44 + + 23/25 Rue Daviel | fax : 01-53-94-20-41 + + 75013 Paris | email:cert@support.renater.fr + =========================================================