๐Ÿ” CVE Alert

CVE-2026-5497

HIGH 7.5

Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm

CVSS Score
7.5
EPSS Score
0.0%
EPSS Percentile
0th

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.

CWE CWE-400
Vendor vllm-project
Product vllm-project/vllm
Published Jun 11, 2026
Stay Ahead of the Next One

Get instant alerts for vllm-project vllm-project/vllm

Be the first to know when new high vulnerabilities affecting vllm-project vllm-project/vllm are published โ€” delivered to Slack, Telegram or Discord.

Get Free Alerts โ†’ Free ยท No credit card ยท 60 sec setup

CVSS v3 Breakdown

CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Affected Versions

vllm-project / vllm-project/vllm
unspecified < 0.19.0

References

NVD โ†— CVE.org โ†— EPSS Data โ†—
huntr.com: https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4 github.com: https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395