vllm-project · vLLM · published 2025-12-01
CVE-2025-66448vLLM vulnerable to remote code execution via transformers_utils/get_config
Routine No exploitation evidence; EPSS 0.7%.
CVE-2025-66448 is not known to be exploited in the wild. EPSS estimates a 0.7% chance of exploitation in the next 30 days, higher than 54% of all CVEs. This vLLM vulnerability: CVSS 7.1 (v3.1), attacks can be automated, a successful attack gives total control of the component. Fixed upstream in vLLM 0.11.1. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.11.1.
Patch events
AI toolingvLLM
vLLM security release: 0.11.1
Upgrade to
0.11.1Why: Vendor security release for server software (most severe: CVE-2025-66448).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.7% (54th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 7.1 (v3.1)CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | Yes | CISA Vulnrichment |
| SSVC technical impact | total | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
< 0.11.1(affected)
Description (from the CVE record)#
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.
Quoted from the CVE Program record.