Vulnerability Monitor

The vendors, products, and vulnerabilities you care about

CVE-2026-22807


vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.


Security Impact Summary

This vulnerability carries a HIGH severity rating with a CVSS v3.1 score of 8.8, indicating it can be exploited remotely over the network with relatively low complexity though user interaction is required and does not require pre-existing privileges . The vulnerability impacts confidentiality (data exposure), integrity (unauthorized modifications), and availability (service disruption) for affected systems. Impacting 1 product from vllm organizations running these solutions should prioritize assessment and patching.

Historical Context

Reported in 2026, this vulnerability emerged during an era marked by increased sophistication in supply chain attacks, cloud infrastructure vulnerabilities, and software-as-a-service (SaaS) security challenges. Security practices during this period emphasized zero-trust architectures, container security, and API protection.


Published

2026-01-21T22:15:49.077

Last Modified

2026-07-21T12:17:29.847

Status

Modified

Source

[email protected]

Severity

CVSSv3.1: 8.8 (HIGH)

Weaknesses
  • Type: Secondary
    CWE-94
  • Type: Secondary
    CWE-94

Affected Vendors & Products
Type Vendor Product Version/Range Vulnerable?
Application vllm vllm < 0.14.0 Yes

References

How SecUtils Interprets This CVE

SecUtils normalizes and enriches National Vulnerability Database (NVD) records by standardizing vendor and product identifiers, aggregating vulnerability metadata from both NVD and MITRE sources, and providing structured context for security teams. For vllm's affected products, we extract Common Platform Enumeration (CPE) data, Common Weakness Enumeration (CWE) classifications, CVSS severity metrics, and reference data to enable rapid vulnerability prioritization and asset correlation. This record contains no exploit code, proof-of-concept instructions, or attack methodologies—only defensive intelligence necessary for patch management, risk assessment, and security operations.