MEDIUMpublic-safe

CVE-2026-105753

NVD: vLLM is an inference and serving engine for large language models. NVD: This issue is fixed in version 0.28.0. OSV: vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core

CVSS
6.5 Severity
MEDIUM EPSS
0.0043 (35) KEV
-

Source-published summary

Possible impact

This medium severity issue needs human triage to confirm exposure, affected versions, and vendor guidance for defensive exposure review.

Affected context

vendor/product: vllm / vllm

Remediation / advisory

Patch confirmed by source text; fixed version context: 0.28.0..

Why it matters

This medium severity issue needs human triage to confirm exposure, affected versions, and vendor guidance for defensive exposure review.; CVSS 6.5 (MEDIUM); EPSS percentile 35; not listed in KEV; Patch confirmed by source text; fixed version context: 0.28.0; sources: NVD, OSV, Vendor Advisory.

What to verify

Confirm affected product/version, vendor advisory, patch or mitigation, and exposure.

Exposure hint

exposure unknown

Impact tags

明示タグなし

Urgency reasons

affected product presentvendor advisory presentrecent updateremediation reference present

Source-derived note

Summary derived from NVD / OSV / Vendor Advisory description; unsafe procedural detail is not shown.

Redaction metadata

source summary used: True
fallback summary used: False
unsafe procedural detail present: false
raw source displayed: false
public summary redacted: true

Remediation handoff

Public-safe static handoff for human/Codex remediation planning. Scan, patch, external execution, and auto remediation are disabled.

Handoff JSON Handoff Markdown Safe Codex prompt

Safety note

This radar shows source-published defensive context only. Exploit procedures, exploit strings, scanner commands, and auto-remediation are not provided.