CVE-2026-130686
vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image Requests
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.
INFO
Published Date :
Nov. 18, 2026, 11:33 a.m.
Last Modified :
Nov. 18, 2026, 11:33 a.m.
Remotely Exploit :
Yes !
Source :
VulnCheck
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 3.1 | HIGH | MITRE-CVE | ||||
| CVSS 4.0 | HIGH | 83251b91-4cc7-4094-a5c7-464a1b83ea10 |
Solution
- Update vLLM to version 0.33.0 or later.
- Ensure request-wide media budget is enforced.
- Monitor resource usage during inference.
- Restrict external image URL processing.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-130686 vulnerability anywhere in the article.