CVE-2025-66448

Summary

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.

Affected Software

Weaknesses

• CWE-94: CWE-94: Improper Control of Generation of Code ('Code Injection')

ADP Enrichment

CISA ADP Vulnrichment

• SSVC:
• Exploitation: none
  • Automatable: yes
  • Technical Impact: total

References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm
• https://github.com/vllm-project/vllm/pull/28126
• https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86

• ←Previous
• Next→