- 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.
- Source
- security@huntr.dev
- NVD status
- Awaiting Analysis
CVSS 3.0
- Type
- Secondary
- Base score
- 7.5
- Impact score
- 3.6
- Exploitability score
- 3.9
- Vector string
- CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Severity
- HIGH
- security@huntr.dev
- CWE-400
- Hype score
- Not currently trending