CVE-2026-100647

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP requests with multi-hundred-megabyte salt values that trigger expensive pickle serialization and SHA-256 hashing, stalling the scheduler thread and denying service to all concurrent requests.
Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

History

06 Oct 2026, 19:46

Type Values Removed Values Added
CPE cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References () https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p - () https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p - Vendor Advisory
References () https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt - () https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt - Third Party Advisory
First Time Vllm vllm
Vllm

26 Sep 2026, 14:16

Type Values Removed Values Added
New CVE

Information

Published : 2026-09-26 14:16

Updated : 2026-10-06 19:46


NVD link : CVE-2026-100647

Mitre link : CVE-2026-100647

CVE.ORG link : CVE-2026-100647


JSON object : View

Products Affected

vllm

  • vllm
CWE
CWE-20

Improper Input Validation