CVEvulnerability
CVE-2026-5497
7.5 HIGH
Official page ↗
- Status
- Modified
- Published
- 2026-06-11
- Last modified
- 2026-10-26
- Assigner
- [email protected]
- CVSS 3.1 (0b0ca135-0b70-47e7-9f44-1890c2a1c46c)
- 7.5 HIGH — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- CVSS 3.0 ([email protected])
- 7.5 HIGH — CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Weaknesses
- CWE-400, CWE-770
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.
Affected configurations
• vllm vllm (>= 0.8.0 < 0.19.0)
Related
References
- https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395 Patch
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4 Exploit, Third Party Advisory
- https://access.redhat.com/security/cve/CVE-2026-5497 access.redhat.com
- https://bugzilla.redhat.com/show_bug.cgi?id=2487813 bugzilla.redhat.com
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4 Exploit, Third Party Advisory
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json security.access.redhat.com