Server-side request forgery in vLLM P2pNcclConnector via X-Request-Id
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- —
- Confidentiality · integrity · availability
- High · None · Low
- Fix status
- Partial Red Hat: 1 fixed, 3 without a fix
Attack profile from CVSS 4.0 · CNA. Fix status from CNA and Red Hat.
Summary
vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery flaw (CWE-918) in which the X-Request-Id header can carry a decode address that forces outbound connections. An API caller can make a P2pNcclConnector prefill worker connect to an attacker host, leaking the NCCL unique_id and KV-cache tensors or blocking the worker.
Written with Claude Haiku 5.5 from the sources below · 2026-11-04
Description from the CNA
vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections by embedding a decode address in the X-Request-Id header. Attackers can make a P2pNcclConnector prefill worker ZMQ-connect to an attacker host, leaking the NCCL unique_id and KV-cache tensors or blocking the worker.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- Yes
- 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 | 0.9.2 to before 0.24.0 | 0.24.0 | Patch available | CNA |
- vllm Vendorvllm-project Affected 0.9.2 to before 0.24.0 Fixed in 0.24.0 Patch available CNA
Remediation
Upgrade vLLM to 0.24.0, which fixes the flaw. Red Hat AI Inference Server 3.5 is fixed by RHSA-2026:94738 (CUDA), RHSA-2026:94721 (Gaudi), RHSA-2026:94717 (Spyre), RHSA-2026:94709 (ROCm) and RHSA-2026:94702 (CPU). Red Hat reports no fix available for Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI).
Written with Claude Haiku 5.5 from the sources below · 2026-11-04
- Fix · CNA vllm (vllm-project) Fixed in 0.24.0
Red Hat 5 advisories
- RHSA-2026:94738 Released 2026-11-03 · Red Hat rating CriticalRed Hat AI Inference 3.5.3 (CUDA)
- Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-cuda-rhel9
- RHSA-2026:94721 Released 2026-11-03 · Red Hat rating CriticalRed Hat AI Inference Tech Preview 3.5.3 (Gaudi)
- Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-gaudi-rhel9
- RHSA-2026:94717 Released 2026-11-03 · Red Hat rating CriticalRed Hat AI Inference 3.5.3 (Spyre)
- Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-spyre-rhel9
Show 2 more Red Hat advisories
- RHSA-2026:94709 Released 2026-11-03 · Red Hat rating CriticalRed Hat AI Inference 3.5.3 (ROCm)
- Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-rocm-rhel9
- RHSA-2026:94702 Released 2026-11-03 · Red Hat rating CriticalRed Hat AI Inference 3.5.3 (CPU)
- Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-cpu-rhel9
Fixed in the same release
Records fixed by the same vendor advisory or release, as the CNA lists them.
- Release ·
vllm-project vllm 0.24.0
5 records Highest priority Priority MEDIUM 1 MEDIUM, 4 LOW
Other records, highest priority first
- TI-2026-80191 Denial of service in vLLM via crafted gRPC logprob token requestsPriority LOW 36
- TI-2026-80190 Denial of service in vLLM Rust gRPC converter via top_nPriority LOW 36
- TI-2026-80192 Denial of service in vLLM via Rust gRPC Generate requestsPriority LOW 35
Vendor assessments
Red Hat
Red Hat rating: Important. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Red Hat AI Inference Server | Affected | No fix yet |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Affected | No fix yet |
| Red Hat OpenShift AI (RHOAI) | Affected | No fix yet |
| Red Hat AI Inference Server 3.5 | Fixed | RHSA-2026:94702, RHSA-2026:94709, RHSA-2026:94717, RHSA-2026:94721, RHSA-2026:94738 |
Not affected: 1 product
- Red Hat OpenShift AI (RHOAI)
Timeline
- 2026-10-25 Threatist record created from CVE-2026-116176
- 2026-10-25 Affected versions changed · Red Hat
- 2026-10-25 CVSS score added · Red Hat
- 2026-10-26 Affected versions changed · Red Hat
- 2026-10-26 Priority changed: MEDIUM → LOW
- 2026-10-27 Alias added: GHSA-3r8v-vh9c-f8hq
- 2026-11-04 Fix available: RHSA-2026:94717 · Red Hat
- 2026-11-04 Fix available: RHSA-2026:94709 · Red Hat
- 2026-11-04 Fix available: RHSA-2026:94738 · Red Hat
- 2026-11-04 Fix available: RHSA-2026:94702 · Red Hat
- 2026-11-04 Fix available: RHSA-2026:94721 · Red Hat
- 2026-11-04 Fix available: Red Hat AI Inference Server 3.5 · Red Hat
- 2026-11-04 CISA SSVC decision points changed
- 2026-11-04 Priority changed: LOW → MEDIUM
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-2026-116176 · CVE Program
- CVE-2026-116176 · NVD
- FIRST EPSS
- GHSA-3r8v-vh9c-f8hq · GitHub Advisory Database · CC BY 4.0
- CVE-2026-116176 · 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