vLLM
vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image Requests
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.
First public PoC
None yetno public PoC found
Public PoCs00 on GitHub
CVSS8.7high · scored by CNA · CWE-400
CISA KEV
Not listednot known exploited
Affected versions and mitigation
From the CVE record and the vendor's references.Affected
vllm-project vllm
- >= 0.6.0, < 0.33.0
Fixed in 0.33.0
Mitigation
Upgrade vllm to 0.33.0 or later.
References
- Vendor advisory github.com/vllm-project/vllm/security/advisori…
Timeline
Days relative to CVE publicationNo public PoC found yet; not in CISA KEV.
PoC repositories
Found on GitHub.No PoC repositories found yet.