Database/AI/ML frameworks & serving
vLLM (prefix cache hash collisions): Crafted prompts collide hashes
CVSS 2.6CVE-2025-25183AI/ML frameworks & servingcurated
Impact
Crafted prompts collide hashes → cache reuse across requests
Who can reach it
Co-tenant on a shared instance
What to do
Same as above — architectural, not patchable away
References
Related entries
- vLLM (prefix cache): Prefix-cache timing side channel leaks other tenants' promptsCVE-2025-46570 · vLLM (prefix cache)Low
- 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
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.