Resource exhaustion in Vllm
CVE-2026-5497
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.
Vulnerability class: DoS (Denial of Service)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS 0.005, 45.8th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm-Project/vllm — versions unspecified
Weakness classification (CWE)
References
- github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395 (Patch)
- huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4 (Exploit, Third Party Advisory)
- access.redhat.com/security/cve/CVE-2026-5497
- bugzilla.redhat.com/show_bug.cgi
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json
- access.redhat.com/errata/RHSA-2026:33524
- access.redhat.com/errata/RHSA-2026:33531