- CVSS
- HIGH · 7.5v3.1CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Published
- 2026-06-11
- Weakness
- CWE-400, CWE-770
- Source
- nvd.nist.gov/vuln/detail/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.
References
- https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
- https://access.redhat.com/errata/RHSA-2026:33524
- https://access.redhat.com/errata/RHSA-2026:33531
- https://access.redhat.com/security/cve/CVE-2026-5497
- https://bugzilla.redhat.com/show_bug.cgi?id=2487813
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-5497 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.