LowVulnerabilityLLM-specific

CVE-2026-114049: vLLM cross-request mask leak in InputBatch.condense() via /invocations

Source: NVD(opens in a new tab)
Identifier: CVE-2026-114049
Published: October 20, 2026
Record updated: October 21, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.

Summary

vLLM before 0.31.0 has a cross-request mask leak in InputBatch.condense(). Remote attackers can leave stale allowed_token_ids rows, so recycled batch slots apply their token allowlist to other clients' unrestricted requests, constraining their outputs.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 3.7(low)
CVSS vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
Attack vector: network
Attack complexity: high
Privileges required: none
User interaction: none
EPSS: Not scored. FIRST had not published an EPSS score for this CVE when it was last checked on October 21, 2026.
Disclosure date: October 20, 2026

Weaknesses and techniques

Weakness (CWE): CWE-440

Classification

Attack type: Other
Attack sophistication: Moderate
AI component targeted: Inference
Impact: Confidentiality,
Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-114049

First tracked: October 21, 2026 at 02:08 AM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Topics

Inference infrastructure

Summary

Mitigation

Topics

Related items