CVE-2026-5497

Description

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.load_base64()` 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.

Severity
HIGH
CVSS v3
7.5
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H · source cna
Exploit chance (EPSS)
0.537%
chance of exploitation in the next 30 days
higher than 45.8% of scored CVEs · 2026-11-17
CISA KEV
Not listed
Public exploit code
Yes
Exploit references (NVD and CNA): 1
Metasploit modules: 0
Nuclei templates: 0

Weakness

CISA SSVC decision points

Exploitationpoc
Automatableyes
Technical impactpartial
Scored2026-06-11

Timeline

  1. 2026-06-11Published by the CNA08:31 UTC
  2. 2026-06-11GitHub advisory published (GHSA-wcwg-c5fc-9vrc)same day
  3. 2026-06-11CISA SSVC decision recordedsame day

The timeline shows what already happened. To be told when this CVE changes next, watch it from the API.

Exploit and advisory records

GitHub advisory GHSA-wcwg-c5fc-9vrc, affected packages:

PackageVulnerable versionsFixed in
PyPI vllmfrom 0.8.0 before 0.19.00.19.0

Affected products

Products listed as vulnerable. Upgrade to the version under "Fixed in", or a later one.

ProductVulnerable versionsFixed in
vllm vllmfrom 0.8.0 before 0.19.0fixed in 0.19.00.19.0

Products and versions as NVD and the vendor that published the CVE list them.

References

Get more CVE data from the API.

Free without a key or signup. Pro adds monitoring and higher limits: pricing.

Sources