CVE-2025-24357

HIGH EPSS 48.3%
Published Jan 27, 20251y ago · Modified Jun 17, 20261w ago
8.8 CVSS 3.1
High
Find Similar
Published Jan 27, 2025 1y ago
Last Modified Jun 17, 2026 1w ago

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.

CVSS Details

Base Score
8.8
Exploitability
2.8
Impact
5.9
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction Required
Scope Unchanged
Confidentiality High
Integrity High
Availability High

Threat Intelligence

EPSS Exploit Probability
48.3% percentile
Exploit & Patch Status
No Known Exploit
Patch Available

Weaknesses 1

CWE-502 Deserialization of Untrusted Data Validation

Affected Products 1

VendorProductVersionRange
vllmvllm* <0.7.0

References 4

  • github.com https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04
    Patch
  • github.com https://github.com/vllm-project/vllm/pull/12366
    Issue TrackingPatch
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54
    Vendor Advisory
  • pytorch.org https://pytorch.org/docs/stable/generated/torch.load.html
    Technical Description

Remediation

  • github.com https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04
    Patch
  • github.com https://github.com/vllm-project/vllm/pull/12366
    Issue TrackingPatch