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
High severity
GitHub Reviewed
Published
Jun 11, 2026
to the GitHub Advisory Database
•
Updated Aug 18, 2026
Description
Published by the National Vulnerability Database
Jun 11, 2026
Published to the GitHub Advisory Database
Jun 11, 2026
Reviewed
Aug 18, 2026
Last updated
Aug 18, 2026
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 processingvideo/jpegdata 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.References