vulnti.work

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 …

Medium CVSS 5.3
CVECVE-2026-100647
First seen2026-09-26 16:31 UTC
Disclosed2026-09-26 14:16 UTC
Last updated2026-09-26 16:31 UTC
Channel statusauto

Summary

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.

In-depth triage

No in-depth report has been generated yet (DR-003 v2 AI pipeline is under construction).

Sources

  • NVD DATABASE

Original Links

Timeline

  1. nvd_ingest NVD