All vulnerabilities

Servers and applications

CVE-2026-105754

Scale-out disaggregated multimodal transport trusts caller-supplied features — shared EngineCore denial of service, encoder-cache poisoning, and transport integrity loss (5 sites)

Severity
Medium 6.5
Published
23 Sept 2026
Last changed
8 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.30.0
Exploit chance
0.3% in the next 30 daysHigher than 19% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Improper input validation (CWE-20)CWE-617Authorization bypass through a user-controlled key (IDOR) (CWE-639)Exposure of a resource to the wrong sphere (CWE-668)
Attack
Over the network · Needs a user account · No user action needed
Attacker can
Take it down
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Also known as
GHSA-ph72-cqr5-qpp7
Sources
NVD, CVE Program, Project advisories (GitHub)

Description

vLLM's disaggregated scale-out transport splits a multimodal request into a trusted render step (POST /v1/chat/completions/render) and a separate generate step (POST /inference/v1/generate). The generate route decodes a caller-supplied features object — serialized encoder tensors (kwargs_data), multimodal hashes (mm_hashes), placeholder ranges (mm_placeholders), and the internal field-processor selection — and forwards it into the engine as if it had come from the trusted renderer, with no rebinding to (or validation against) the active model's renderer contract. Because the two routes are ordinary auth-guarded HTTP endpoints (the /inference prefix is registered by default on generate-capable servers), any authenticated caller can submit an otherwise-valid render body with a single forged field.

Depending on which field is forged, this produces:

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
vLLMServers and applications · cna:vllm-project|vllm
  • Every version before 0.30.0
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version before 0.30.0
vLLMServers and applications · github:vllm-project/vllm
  • Every version before 0.30.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-105754
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-105754
  • GitHub Advisory Database https://github.com/advisories/GHSA-ph72-cqr5-qpp7
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-ph72-cqr5-qpp7