HIGHCVSS 7.5
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.
Published 2026-11-18 · last modified 2026-11-18
← Get alerted the moment a CVE hits your gear — subscribe freeNcerio by BeyondNets · data from NVD, CISA KEV, EPSS.