Deserialization of Untrusted Data in vLLM - CVE-2026-115912
Published: November 9, 2026
Vulnerability details
The vulnerability allows an authenticated remote attacker to execute arbitrary Python code in a vLLM worker process.
The vulnerability exists due to unvalidated shared-memory handles reaching unsafe deserialization in the multimodal cache when --mm-processor-cache-type shm is enabled. An authenticated remote attacker can stage malicious bytes through public inference requests and submit a forged handle to trigger code execution, even with VLLM_ALLOW_INSECURE_SERIALIZATION=0.