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.

How to fix CVE-2026-5497

To remediate CVE-2026-5497, upgrade the affected package to a fixed version below.

• —upgrade to 0.19.0 or later

Is CVE-2026-5497 being exploited?

Low — EPSS is 0.5%, meaning exploitation activity has not been observed at scale.

Affected packages (1)

• >= 0.8.0, < 0.19.0

CVSS scores

References (5)

• EXPLOIThuntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
• PATCHgithub.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
• REPORTbugzilla.redhat.com/show_bug.cgi?id=2487813
• WEBaccess.redhat.com/security/cve/CVE-2026-5497