CVE-2026-37237
vLLM Memory Exhaustion Denial of Service
Description
vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetch_audio and AsyncMediaIO.fetch_image functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read() without enforcing a maximum response size, allowing an attacker to exhaust server memory by providing a URL to an arbitrarily large file.
INFO
Published Date :
Aug. 28, 2026, 4:17 p.m.
Last Modified :
Aug. 28, 2026, 4:17 p.m.
Remotely Exploit :
No
Source :
[email protected]
Affected Products
The following products are affected by CVE-2026-37237
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.
No affected product recoded yet
Solution
- Update vLLM to version 0.17.1 or later.
- Apply patches for AsyncMediaIO.fetch_audio and fetch_image functions.
- Enforce maximum response size for fetched media.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-37237.
| URL | Resource |
|---|---|
| https://github.com/vllm-project/vllm/blob/main/vllm/multimodal/inputs.py | |
| https://github.com/vllm-project/vllm/pull/36506 | |
| https://s00me00ne.com/cve/cve-2026-37237/ |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-37237 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-2026-37237
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-2026-37237 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-37237 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.
-
New CVE Received by [email protected]
Aug. 28, 2026
Action Type Old Value New Value Added Description vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetch_audio and AsyncMediaIO.fetch_image functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read() without enforcing a maximum response size, allowing an attacker to exhaust server memory by providing a URL to an arbitrarily large file. Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/37xxx/CVE-2026-37237.json">CVE-2026-37237</a> Added Reference https://github.com/vllm-project/vllm/blob/main/vllm/multimodal/inputs.py Added Reference https://github.com/vllm-project/vllm/pull/36506 Added Reference https://s00me00ne.com/cve/cve-2026-37237/