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.

CVSS 4.0

6.9CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N

CVSS 3.1

7.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

EPSS

0.3% chance of exploitation in the next 30 days; higher than 28% of CVEs (scores of 2026-10-25)

CWE

CWE-20

Published

2026-09-26

Modified

2026-10-06

Record from

the NVD, synced 2026-10-19

Affected

• vllm:vllm

References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p
• https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt

Check your stackJSON