CVE Feed
8.7 High

vLLM from 0.6.0 before 0.33.0 lacks a request-wide media budget, allowing remote inference clients to exhaust frontend resources by…

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 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.

Part of the AI stack

This affects vLLM, in Inference & serving.

Assessment

CVSS
8.7 (v4.0)
Severity
High
Known exploited
Not listed in CISA KEV
Exploit availability
Nothing found in Exploit-DB, Metasploit, Nuclei or public PoC repositories
Published
18 November 2026
Last updated
18 November 2026
Affected
vllm-project · vllm
Assigner
VulnCheck

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

At the source

References

Community proofs of concept

No community proof of concept yet. If you have one for a published vulnerability and the right to share it, add it below — it will appear here once reviewed.

Submit a proof of concept
Before you submit *

Query this programmatically

Agents can read this through the MCP endpoint, or over HTTP:

curl https://cve.zerocrew.in/api/cve/CVE-2026-130686