vLLM: vLLM is vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded…
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-2026-5497
- Affects
- vLLM
- Known exploited
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Published
- Record first published by the source
- June 11, 2026
- Source last modified
- October 26, 2026
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.
Description quoted from the NVD record.
Who is affected
vLLM is software that runs AI language models on a server so that other programs can send them questions and get answers. This flaw affects vLLM versions 0.8.0 and later. It is in the part that handles video sent as a series of still images inside a chat request, which is reachable through the chat feature that works like OpenAI's. Anyone who can reach the server, with no login needed, could send one request packed with thousands of images, making the server use up its memory and crash. This flaw is rated High.
What to do
- Find out who installed or runs vLLM for your organization: a staff member, or an IT provider or vendor who manages it for you.
- If you run it yourself, check which version is installed. Versions 0.8.0 and later are affected by 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 you, send them this advisory and ask when the update will be done.
Analysis written from the source record as of October 26, 2026 and reviewed before publishing.