vLLM: VLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory…
vLLM
More for vLLM RSS feed for vLLM
- Severity
- High, CVSS 7.5
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Record
- CVE-2026-37237
- Affects
- vLLM
- Known exploited
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Published
- Record first published by the source
- August 28, 2026
- Source last modified
- September 29, 2026
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.
Description quoted from the NVD record.
Who is affected
vLLM is software that runs AI language models on a server so that other apps and people can send them requests. This flaw affects vLLM versions up to and including 0.17.0. The problem is in the part of vLLM that downloads images and audio from links supplied by users: it does not limit how large a downloaded file can be. An attacker over the network could send a link to an extremely large file and make the server run out of memory, so it stops working for everyone. This flaw is rated High.
What to do
- If someone in your organization installed or runs vLLM, they should check which version is in use. Any version up to and including
0.17.0has this flaw. - No fixed version is named for this flaw yet, so check the vendor advisory linked on this page for a fixed release and install it as soon as one is available.
- If an IT provider or vendor runs vLLM for your organization, send them this advisory and ask when the update will be done.
Analysis written from the source record as of September 29, 2026 and reviewed before publishing.