CVE-2026-130686
18.11.2026, 12:17
vLLM from 0.6.0 before 0.33.0 lacks a request-wide media budget, allowing remote inference clients to exhaust frontend resources by submitting many remote image URLs in one request. Attackers can send a compact request to /v1/messages or /v1/responses that forces downloading and decoding of every image before prompt-length admission, exhausting memory, CPU, and connections.Enginsight
Early Detection
Affected products identified ahead of NVD analysis through intelligence sources
(CNA/ADP records, vendor advisories, Enginsight analysis).
| Vendor | Product | Version | Source |
|---|---|---|---|
| vllm | vllm | 0.6.0 ≤ 𝑥 < 0.33.0 | CNA |