Vulnerability · Published Aug 13, 2026 · Assigned by GitHub_M
CVE-2026-73559vLLM: Completion prompt lists fan out into unbounded engine requests
Medium 6.5
In plain English
A medium-severity uncontrolled resource consumption in vllm from vllm-project. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 48% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | vllm | 0.26.0 | GHSA-87x5-vmc3-756j |
| PyPI | vllm | 0.26.0 | PYSEC-2026-3704 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.19.0, < 0.26.0 |
Weakness: CWE-400 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j x_refsource_CONFIRM
- https://github.com/vllm-project/vllm/pull/47845 x_refsource_MISC
- https://github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e x_refsource_MISC
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0 x_refsource_MISC