Medium · CVSS 6.3CVE-2026-114049

vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condenseCVE-2026-114049

Answer in brief

CVE-2026-114049 records a Medium severity (CVSS 6.3) vulnerability in vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense. The current sources do not mark it as known exploited. The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Oct 21, 2026Updated Oct 21, 2026Source checked Oct 21, 2026First seen by HOL Oct 21, 2026Material review Oct 21, 2026

Upstream Advisory

Key facts

Risk: Medium · CVSS 6.3
Exploitation: Not marked as known exploited
Affected software: 1 mapped package or product
Fix availability: Available

Why this deserves its current priority

CVSS is 6.3. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
vllm-project/vllmgeneric	>=0 <0.31.0	0.31.0

Recommended response

Check inventory. Check lockfiles and deployed manifests for vllm-project/vllm.
Review the reported fix. Update vllm-project/vllm to 0.31.0 if you use the affected versions. Test the change in a non-production environment first.

Evidence timeline and material changes

Published upstream
Oct 21, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Oct 21, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Oct 21, 2026

Sources and claim methodology

Upstream source description

vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycled batch slots apply their token allowlist to victims' unrestricted requests.

Quoted source text, attributed separately from HOL analysis.