vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt
Historical advisory recorded 23 Oct 2026 15:48:27 UTC. Read the latest advisory.
cve-program · CVE-2026-100647
PublishedvLLM 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.
Read the publisher's advisoryAffected versions, risk and source history
Related advisories and sources
Publishers link these advisories through the identifiers shown below. A shared identifier or date alone does not tell you whether your software is affected or whether the advisories describe the same cause.
CVE-2026-100647 · CVE overview and exploitation status
cve-program · CVE-2026-100647
This historical advisory does not include today's related changes. Open the latest advisory to find current connections.