VDB
CVE-2026-73559
CVE-2026-73559
PUBLISHED
CVSS 6.5 MEDIUM
Reported by GitHub_M · Published August 13, 2026
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.
Risk Scores
CVSS 3.1
6.5
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.19.0, < 0.26.0 |
| PyPI | vllm | 0.19.0 |
| vllm-project | vllm | >= 0.19.0, < 0.26.0 |
| chainguard | tritonserver-backend-vllm-cuda-13.0 | 0 |
| chainguard | vllm-openai-cuda-12.9 | 0 |
Timeline
- Aug 13, 2026 CVE Published
- Aug 14, 2026 Coalition ESS Score
- Aug 14, 2026 CVE Updated
- Aug 20, 2026 Security Advisory
- Aug 24, 2026 EPSS Score
- Aug 26, 2026 EPSS Score
- Aug 30, 2026 EPSS Score
- Sep 4, 2026 EPSS Score
- Sep 9, 2026 EPSS Score
- Sep 10, 2026 EPSS Score
- Sep 12, 2026 EPSS Score
- Sep 16, 2026 EPSS Score
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
- https://nvd.nist.gov/vuln/detail/CVE-2026-73559 advisory
- https://github.com/advisories/GHSA-87x5-vmc3-756j advisory