6.5
MEDIUM CVSS 3.1
CVE-2026-73559
vLLM: Completion prompt lists fan out into unbounded engine requests
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.

INFO

Published Date :

Aug. 13, 2026, 4:19 p.m.

Last Modified :

Aug. 14, 2026, 5:20 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-73559 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Vllm-project vllm
1 Vllm vllm
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 134c704f-9b21-4f2e-91b3-4a467353bcc0
CVSS 3.1 MEDIUM [email protected]
CVSS 3.1 MEDIUM MITRE-CVE
Solution
Update vLLM to version 0.26.0 or later to fix denial-of-service vulnerability.
  • Update vLLM to version 0.26.0 or later.
  • Apply security patches provided by the vendor.
  • Monitor resource utilization after update.
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-73559 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-73559 weaknesses.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-73559 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-73559 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0

    Aug. 14, 2026

    Action Type Old Value New Value
    Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
    Added SSVC {'id': 'CVE-2026-73559', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'no'}, {'technicalImpact': 'partial'}], 'version': '2.0.3', 'timestamp': '2026-08-14T16:51:10.709750Z'}
  • New CVE Received by [email protected]

    Aug. 13, 2026

    Action Type Old Value New Value
    Added Affected [{'vendor': 'vllm-project', 'product': 'vllm', 'versions': [{'status': 'affected', 'version': '>= 0.19.0, < 0.26.0'}]}]
    Added 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.
    Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
    Added CWE CWE-400
    Added Reference https://github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
    Added Reference https://github.com/vllm-project/vllm/pull/47845
    Added Reference https://github.com/vllm-project/vllm/releases/tag/v0.26.0
    Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.