Live › vulnerability › CVE-2026-114054
Go to dashboardvLLM before 0.31.0 builds shared cache keys from caller-controlled values such as an EXIF ImageID or cache_salt. An authenticated attacker can craft a value that matches another request's cache entry and receive that request's processed media or reuse its first-block KV state.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-23 21:57 UTC. All times on this page are UTC.
Teams that run vLLM as a multi-user or multi-tenant inference server where authenticated callers can send multimodal inputs or set cache_salt. A single-tenant deployment where every caller is trusted is at much lower risk. unknown beyond that.
No product ranges from the sources yet.
pip show vllm or python -c "import vllm; print(vllm.__version__)", and flag anything below 0.31.0.cache_salt or multimodal image inputs from untrusted callers.0.31.0 or later.cache_salt or EXIF-based image input to other tenants.Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
vLLM before 0.31.0 contains a cache aliasing vulnerability that allows authenticated attackers to collide shared cache keys by supplying caller-controlled values such as EXIF ImageID or cache_salt. Attackers can set a UUID EXIF ImageID to receive another request's cached processed media, or match cache_salt to a LoRA name to reuse first-block KV state.
This page as .md · .json · in your agent: get_signal("CVE-2026-114054")
NVD data is provided by NIST and is public domain · EPSS scores by FIRST, used with attribution. Posts quoted belong to their authors.