VDB

CVE-2026-105756

CVE-2026-105756 PUBLISHED CVSS 6.5 MEDIUM

Reported by github_m · Published October 5, 2026

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. This issue is fixed in version 0.30.0.

Fixed versions

Upgrade to a fixed version or later. Language registries are listed first, then Linux distributions, then vendor products.

PackageEcosystemFixed in
tritonserver-backend-vllm-cuda-13.0Chainguard25.11-r17

Risk scores

CVSS 3.1
6.5
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Affected products

VendorProductVersions
vllm-projectvllm< 0.30.0
chainguardtritonserver-backend-vllm-cuda-13.00
vllm-projectvllm0
chainguardvllm-openai-cuda-13.00
chainguardpy3-vllm-cuda-12.4*
chainguardlmcache-cuda-12.8*
PyPIvllm0
chainguardvllm-cuda-13.20

Timeline

  • Oct 5, 2026 CVE Published
  • Oct 6, 2026 EPSS Score (11 in total, the first dated here)
  • Oct 6, 2026 Coalition ESS Score
  • Oct 6, 2026 CVE Updated
  • Oct 31, 2026 Security Advisory

Query this with the API

The same record, from the CLI:

vulnetix vdb vuln CVE-2026-105756
vulnetix vdb fixes CVE-2026-105756

Or with curl, using the org id and key from your account page:

curl -s -H "Authorization: ApiKey ${VULNETIX_ORG_ID}:${VULNETIX_API_KEY}" \
  "https://api.vdb.vulnetix.com/v2/vuln/CVE-2026-105756/fixes/registry"

The Community plan is free and allows 50 queries a day. Get a free API key · API quickstart

Look up in the Resolve Platform →
$ Lookup Community · 50/day Open Lookup ›