CVE-2026-114049
lowvLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stal…
Vendor / product: Vllm — vllm
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.
CVSS
3.7
3.7 (CVSS v3.1)
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N Severity source: NVD CVSS v3.1 (disclosure@vulncheck.com)
Timeline (UTC)
Published: 2026-10-21 01:17
Modified: 2026-11-03 18:43
NVD status: Analyzed
Last synced 1 day ago
Verified against the source API 2026-11-03 18:50 UTC
Exploitation
Not listed in CISA KEV (as of last catalog sync)
Absence from KEV does not mean a CVE is not exploited. Exploitation status: unknown (no authoritative evidence in our sources).
Affected products
vllm / vllm <0.31.0
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6cxc-2vcg-w5qc disclosure@vulncheck.com
- https://www.vulncheck.com/advisories/vllm-before-0.31.0-stale-allowed-token-ids-mask-via-i... disclosure@vulncheck.com
Data sources
NVD CVE API 2.0 — fetched 2026-11-03 18:50 UTC · record ↗