| Component | 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 |
| Published (NVD) | 2026-08-28 |
| Last modified | 2026-09-29 |
| Affected versions | vllm <= 0.17.0 |
| Fixed in | see the vendor advisory |
| Weakness | CWE-400 |
| CISA KEV | not listed |
NVD 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.
What to do
- NVD lists no fixed version yet: follow the vendor advisory below and keep vLLM off the public internet until a fix ships.
- Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-37237
- https://github.com/vllm-project/vllm/pull/36506
- https://s00me00ne.com/cve/cve-2026-37237/
- https://github.com/vllm-project/vllm/blob/main/vllm/multimodal/inputs.py
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...