GHSA-rqcj-6434-qfchHighCVSS 7.5

vLLM from 0.6.0 before 0.33.0 lacks a request-wide media budget, allowing remote inference...

Published
November 18, 2026
Last Modified
November 18, 2026

🔗 CVE IDs covered (1)

📋 Description

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.

🔗 References (3)