UTC
High

vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator

CVE-2025-24357 · GHSA-rh4j-5rhw-hr54 · published 2025-01-27 · updated 2025-06-30

Severity
High
CVSS score
7.5
Chance of exploitation (EPSS)
0.89%
Fixed in
0.7.0
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

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.

What to do

Upgrade vllm to 0.7.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Affected
PackageRegistryAffectedFixed in
vllmPyPI< 0.7.00.7.0

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].