Threats Tagged 'cve-2026-105756'
View all threats tagged with 'cve-2026-105756'. Filter and sort to focus on specific types of threats.
Stop chasing alerts. Route them.
Start free, then upgrade once to turn Radar into an automated delivery engine for your security stack.
Custom feeds / Automations: email, Slack, webhooks, SIEM/MISP / API access (baseline limits)
API access activates after upgrading in Console -> Billing.
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.
Filter Threats
Narrow down the results by type, severity, or affected countries
Threats Tagged 'cve-2026-105756'
Click on any threat for detailed analysis and mitigation recommendations
vLLM versions prior to 0.30.0 have an improper input validation vulnerability in the OpenAI-compatible request models. Specifically, the cache_salt parameter does not enforce required character and length restrictions, which can cause an uncaught ValueError during scheduler cache lookup when using the LMCache-MP connector. This leads to termination of the EngineCore and denial of service to all concurrent users. The issue is fixed in version 0.30.0. Join the discussion | CVE Database V5 | 10/05/2026, 22:49:59 UTC Added: 10/05/2026, 23:04:01 UTC |
Showing 1 to 1 of 1 result