NetSight
high8.7

CVE-2026-130686

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 imag…

Impact

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.

An attacker can exploit this over the network, without logging in, without any action by a user. If it succeeds: high risk of outages.

Affected products · Vllm-project

ProductAffected versions
Vllm
from 0.6.0 before 0.33.0

Weakness classification

References