Denial of service in vLLM via prompt embeds on XD-RoPE models
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- High
- Attack requirements
- Present
- Impact type
- Denial of service
- Confidentiality · integrity · availability
- None · None · High
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-617.
Summary
vLLM from 0.28.0 before 0.30.0 contains a reachable assertion in GPUModelRunner._init_xdrope_positions (CWE-617). A remote attacker with no privileges can crash the engine by sending a /v1/completions request that contains only prompt_embeds to XD-RoPE models run with --enable-prompt-embeds. The crash terminates the EngineCore and the API server for all clients.
Written with Claude Haiku 5.5 from the sources below · 2026-11-13
Description from the CNA
vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the engine by submitting embeddings-only requests. Attackers can send a /v1/completions request containing only prompt_embeds to XD-RoPE models with --enable-prompt-embeds, terminating the EngineCore and API server for all clients.
Why it matters now
SSVC decision points
Not available: CISA has not published SSVC decision points for this record.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| vllm-project | vllm | 0.28.0 to before 0.30.0 | 0.30.0 | Patch available | CNA |
- vllm Vendorvllm-project Affected 0.28.0 to before 0.30.0 Fixed in 0.30.0 Patch available CNA
Remediation
Upgrade vLLM to version 0.30.0 or later, which is the first fixed version.
Written with Claude Haiku 5.5 from the sources below · 2026-11-13
- Fix · CNA vllm (vllm-project) Fixed in 0.30.0
Timeline
- 2026-11-13 Threatist record created from CVE-2026-126398
- 2026-11-13 Alias added: GHSA-pjrq-r86m-9r53
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-2026-126398 · CVE Program
- CVE-2026-126398 · NVD
- FIRST EPSS
- GHSA-pjrq-r86m-9r53 · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences