vLLM is vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the VideoMediaIO.load_base64() method

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

7.5 · CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

EPSS

• CVE-2026-5497: 0.54% estimated exploitation activity in the next 30 days; percentile 45.28 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the VideoMediaIO.loadbase64() method. When processing video/jpeg data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.

Published by the source

11 Jun 2026, 12:32 UTC

Last modified by the source

18 Aug 2026, 20:40 UTC

Source last checked

26 Oct 2026, 13:50 UTC

1. Revision 2 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-wcwg-c5fc-9vrc

2. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-wcwg-c5fc-9vrc

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-5497

Advisory: vLLM is vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method
IDs: CVE-2026-5497, GHSA-wcwg-c5fc-9vrc
Record: https://patchnext.com/advisories/cve-2026-5497 (revision 2, source checked 26 Oct 2026, 13:50 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: High (CVSS 7.5)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: vllm 0.19.0. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI vllm: affected >= 0.8.0, < 0.19.0; fixed in 0.19.0

## Suggested inspection (read-only)
- `python -m pip show vllm`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on vllm.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-wcwg-c5fc-9vrc (OSV record GHSA-wcwg-c5fc-9vrc lists affected ranges: PyPI vllm >=0.8.0 <0.19.0 (fixed))
- Verified: https://github.com/advisories/GHSA-wcwg-c5fc-9vrc (GitHub-reviewed advisory GHSA-wcwg-c5fc-9vrc lists affected ranges: PyPI vllm >=0.8.0 <0.19.0)

Commands are suggestions: review each one before running it.