CVSS 3.0
Вероятност да бъде експлоатирана в следващите 30 дни (EPSS)
Атакува се
Време до експлоатация
Атакува се по мрежата, без особени условия, без вход и без действие от потребителя.
- Експлоатация: има публичен пример за експлоатация
- Атаката може да се автоматизира
Описание
Оригинално описание
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.
Засегнати продукти
- vllm-project vllm-project/vllm: unspecified преди 0.19.0
- Red Hat Red Hat AI Inference Server
- Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3
- Red Hat Red Hat OpenShift AI (RHOAI)
Вид слабост
История
- 11 юни 2026 Публикувано
Други уязвимости в vllm-project vllm-project/vllm
Първоизточници
- https://www.cve.org/CVERecord?id=CVE-2026-5497
- https://nvd.nist.gov/vuln/detail/CVE-2026-5497
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
- https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
- https://access.redhat.com/security/cve/CVE-2026-5497
- https://bugzilla.redhat.com/show_bug.cgi?id=2487813
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json