Tools AI Risk Radar ai-incident-0161
Incident record
vLLM validates media features in split inference deployments
- Severity
- Medium
- Status
- Patched
- Type
- Infra Vuln
- Target
- vllm
- Actor
- researcher
- CVE
- CVE-2026-105754
What happened
A caller able to reach the internal generation endpoint could supply forged media features that the engine trusted as renderer output. Depending on the field, this could crash the engine or corrupt the request’s interpretation.
vllm: affected < 0.30.0; fixed in 0.30.0. The date shown is the maintainer’s original disclosure date. Its advisory assigns 6.5 under CVSS 3.1.
Sources
- Primary disclosuregithub.com/vllm-project/vllm/security/advisories/GHSA-ph72-c…
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