CVE-2026-73559
Last modified
CVE-2026-73559 is a medium-severity vulnerability rated 6.5/10 on the CVSS scale. vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. EPSS estimates a 0.39% chance of exploitation in the next 30 days.
Description
vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. This issue is fixed in version 0.26.0.
Metrics
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Weakness Enumeration
Affected Software
Source: CNA advisory (CVE.org). NVD analysis pending.
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.19.0, < 0.26.0 |
References
Timeline
- Published
- Last Modified
- Status
- Received
Frequently Asked Questions
What is CVE-2026-73559?
How severe is CVE-2026-73559?
How do I fix CVE-2026-73559?
How Strix Helps
- How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
- Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
- PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
- AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.
Related CVEs from 2026
- CVE-2026-73542Multiple SEIKO EPSON printers and scanners contain revoked r…3.7
- CVE-2026-7355Use after free in Media in Google Chrome prior to 147.0.7727…8.8
- CVE-2026-73555vLLM is an inference and serving engine for large language m…5.3
- CVE-2026-73556vLLM is an inference and serving engine for large language m…5.3
- CVE-2026-73557vLLM is an inference and serving engine for large language m…6.3
- CVE-2026-73558vLLM is an inference and serving engine for large language m…5.3
- CVE-2026-7356Use after free in Navigation in Google Chrome prior to 147.0…8.8
- CVE-2026-73560vLLM is an inference and serving engine for large language m…6.5
- CVE-2026-73561Hub is a Node.js WebSocket server and client with added feat…7.5
- CVE-2026-73562Mongoose is a MongoDB object modeling tool designed to work …6.5
- CVE-2026-73563Backstage is an open framework for building developer portal…4.7
- CVE-2026-73564frp is a fast reverse proxy. From 0.53.0 until 0.70.1, frp's…8.7
Are you affected by CVE-2026-73559?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST