HighVulnerabilityLLM-specific
CVE-2026-116180: vLLM denial of service through prompt_logprobs on cached prefixes
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-116180
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.3%
Summary
vLLM from 0.8.5 before 0.31.0 contains a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, causing tokenizer decode to raise OverflowError, which crashes EngineCore and drops all co-tenant requests.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
Related items
- HighCVE-2026-123356: GROBID unauthenticated thread exhaustion through /api/modelTraining endpointSimilar attack · NVD/CVE Database
- MediumCVE-2026-83494: training-operator immutability check bypass in PyTorchJob ValidateUpdate webhookSimilar attack · NVD/CVE Database
- CriticalCVE-2026-48705: MONAI PydicomReader affine computation accepts non-finite DICOM valuesSimilar attack · NVD/CVE Database
- LowCloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource ExhaustionSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- MediumThe Rise of LLMJacking: How Threat Actors Monetize Compromised Cloud and Model ResourcesSimilar attack · Google Threat Intelligence