Read the docs
TI-2025-18100 Aliases CVE-2025-24357GHSA-rh4j-5rhw-hr54

vLLM allows a malicious model RCE by torch.load in hf_model_weights_iterator

Priority MEDIUM 42CWE-502Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
Required
Attack complexity
Low
Impact type
Code execution
Confidentiality · integrity · availability
High · High · High
Fix status
Partial Red Hat: 1 without a fix

Attack profile from CVSS 3.1 · NVD. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-502.

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 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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00893 59th percentileScored 2026-11-07
Fix Partial vllm (vllm-project): 0.7.0vllm (PyPI): 0.7.0Red Hat: 1 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Total

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
vllm-projectvllmbefore 0.7.00.7.0Patch availableCNA
—vllm (PyPI)before 0.7.00.7.0Patch availableGHSA-rh4j-5rhw-hr54
  • vllm Vendorvllm-project Affected before 0.7.0 Fixed in 0.7.0 Patch available CNA
  • vllm (PyPI) Vendor— Affected before 0.7.0 Fixed in 0.7.0 Patch available GHSA-rh4j-5rhw-hr54

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*before 0.7.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions before 0.7.0 Vulnerable ·vLLM

Remediation

  • Fix · CNA vllm (vllm-project) Fixed in 0.7.0
  • Fix · GHSA-rh4j-5rhw-hr54 vllm (PyPI) Fixed in 0.7.0 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Important. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat Enterprise Linux AI (RHEL AI)AffectedNo fix yet
Not affected: 1 product
  • Red Hat Enterprise Linux AI (RHEL AI)

Timeline

  1. 2026-10-02 Threatist record created from CVE-2025-24357
  2. 2026-10-03 Alias added: GHSA-rh4j-5rhw-hr54

References

Patch 2

Advisory 2

Other 4

  • TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
  • TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
  • TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
  • TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
  • TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
  • TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences