CVE-2026-100647 — vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt
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 …
Published: 2026-09-26 · CVSS: 6.9 · CVSS 4.0
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.
Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7