High severity · published Aug 28, 2026
CVE-2026-37237
vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion
7.5
CVSS
0.7%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
None
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.7% · higher than 54% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
Vllm · Vllm
through 0.17.0 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-37237
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-37237
Product
https://github.com/vllm-project/vllm/blob/main/vllm/multimodal/inputs.py
Issue Tracking
https://github.com/vllm-project/vllm/pull/36506
Third Party Advisory
https://s00me00ne.com/cve/cve-2026-37237/
More from Vllm
9.8
CVE-2026-115915
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
9.8
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
9.8
CVE-2025-47277
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache…