CVE-2026-130686 PUBLISHED

vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image Requests

Assigner: VulnCheck
Reserved: 17.11.2026 Published: 18.11.2026 Updated: 18.11.2026

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.

Metrics

CVSS Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
CVSS Score: 8.7

Product Status

Vendor vllm-project
Product vllm
Versions Default: unaffected
  • affected from 0.6.0 to 0.33.0 (excl.)
  • Version 0.33.0 is unaffected

Credits

  • dohashelby reporter
  • jperezdealgaba coordinator

References

Problem Types

  • Uncontrolled Resource Consumption CWE