Database/AI/ML frameworks & serving
vLLM (prefix cache): Prefix-cache timing side channel leaks other tenants' prompts
CVSS 2.6CVE-2025-46570AI/ML frameworks & servingcurated
Impact
Prefix-cache timing side channel leaks other tenants' prompts
Who can reach it
Co-tenant issuing timed prompts against a shared serving instance
What to do
No clean fix while prefix caching is shared. Do not share a vLLM instance across tenants — the cache is a cross-tenant channel
References
Related entries
- JupyterHub: hyphenated username collides with another user's named-server OAuth clientCVE-2026-108752 · JupyterHub (named-server OAuth client id derivation)Low
- iFlytek Astron Agent: workflow resume endpoint accepts another application's event_idCVE-2026-108864 · iFlytek Astron Agent (POST /workflow/v1/resume)Low
- vLLM: unvalidated bad_words token indices corrupt logits of other in-flight requestsCVE-2026-93989 · vLLM sampling parameters (bad_words token index validation)Low
- Langflow: authenticated user reaches eval() through component input options and runs code on the hostCVE-2026-101861 · Langflow schema.py (eval() on component input option values)Low
- vLLM: out-of-bounds read in Mamba2 mixer reachable from a completions requestCVE-2026-105775 · vLLM (Mamba2 mixer conv_ssm_forward, completions request handler)Low
- vLLM: engine crash via the penalty handler when prompt embeds are combined with penaltiesCVE-2026-105922 · vLLM (penalty handler, get_token_bin_counts_and_mask in model_executor/layers/utils.py)Low
This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.