Tools AI Risk Radar ai-incident-0163
Incident record
vLLM fixes interference between document-scoring requests
- Severity
- Medium
- Status
- Patched
- Type
- Infra Vuln
- Target
- vllm
- Actor
- researcher
- CVE
- CVE-2026-105755
What happened
Concurrent callers using the same request identifier could overwrite cached query data in flash late-interaction scoring. The victim’s documents could then be scored against the attacker’s query, or the request could fail.
vllm: affected < 0.30.0; fixed in 0.30.0. The date shown is the maintainer’s original disclosure date. Its advisory assigns 4.2 under CVSS 3.1.
Sources
- Primary disclosuregithub.com/vllm-project/vllm/security/advisories/GHSA-2phq-3…
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