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.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-20"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/100xxx/CVE-2026-100647.json"
}