Tools AI Risk Radar ai-incident-0160
Incident record
vLLM fixes video requests that exhaust CPU and memory
- Severity
- Medium
- Status
- Patched
- Type
- Infra Vuln
- Target
- vllm
- Actor
- researcher
- CVE
- CVE-2026-105760
What happened
A caller could select the GLMGA video sampler and supply excessive sampling values, delaying other media requests. The deployment must accept these video options; a configured API key still controls access.
vllm: affected >= 0.23.0rc2, < 0.30.0; fixed in 0.30.0. The date shown is the maintainer’s original disclosure date. Its advisory assigns 5.3 under CVSS 3.1.
Sources
- Primary disclosuregithub.com/vllm-project/vllm/security/advisories/GHSA-58v5-2…
One record from the AI Risk Radar, maintained by the Security Desk.Data: CSV · JSON ·RSS · CC BY 4.0 with attribution to YFarmX.Tracker updated · 13 October 2026