Stale token allowlists leak across requests in vLLM
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- High
- Attack requirements
- Present
- Impact type
- —
- Confidentiality · integrity · availability
- None · Low · None
- Fix status
- Partial Red Hat: 3 without a fix
Attack profile from CVSS 4.0 · CNA. Fix status from CNA and Red Hat.
Summary
vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() (CWE-440). Unauthenticated remote attackers can submit concurrent constrained generate requests through /invocations, so recycled batch slots apply stale token allowlists to other clients' unrestricted requests. This lets attackers constrain the outputs of other clients.
Written with Claude Haiku 5.5 from the sources below · 2026-10-28
Description from the CNA
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| vllm-project | vllm | before 0.31.0 | 0.31.0 | Patch available | CNA |
- vllm Vendorvllm-project Affected before 0.31.0 Fixed in 0.31.0 Patch available CNA
Remediation
Upgrade vLLM to version 0.31.0. Red Hat has no fix plan available for Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI).
Written with Claude Haiku 5.5 from the sources below · 2026-10-28
- Fix · CNA vllm (vllm-project) Fixed in 0.31.0
Fixed in the same release
Records fixed by the same vendor advisory or release, as the CNA lists them.
- Release ·
vllm-project vllm 0.31.0
7 records Highest priority Priority MEDIUM 3 MEDIUM, 4 LOW
Other records, highest priority first
- TI-2026-78668 Uncontrolled resource use in vLLM lets clients exhaust server memoryPriority MEDIUM 44
- TI-2026-78665 Memory exhaustion in vLLM MOSS-Audio serving through /tokenizePriority MEDIUM 44
- TI-2026-78666 Remote code execution in vLLM via mm_processor_kwargs.code_revisionPriority MEDIUM 42
Vendor assessments
Red Hat
Red Hat rating: Low. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Red Hat AI Inference Server | Affected | No fix yet: Fix deferred |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Affected | No fix yet: Fix deferred |
| Red Hat OpenShift AI (RHOAI) | Affected | No fix yet: Fix deferred |
Timeline
- 2026-10-21 Threatist record created from CVE-2026-114049
- 2026-10-21 Affected versions changed · Red Hat
- 2026-10-21 CVSS score added · Red Hat
- 2026-10-22 Priority changed: MEDIUM → LOW
- 2026-10-28 CISA SSVC decision points changed
References
More vllm-project vulnerabilities
- TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
- TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
- TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
- TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
- TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
- TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
Sources
- CVE-2026-114049 · CVE Program
- CVE-2026-114049 · NVD
- FIRST EPSS
- CVE-2026-114049 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences