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
| Product | Affected versions |
|---|---|
| Vllm | from 0.6.0 before 0.33.0 |