CVE-2025-46570: vLLM timing side channel in prefix cache matching during prefill

Summary

CVE-2025-46570 affects vLLM, an inference and serving engine for large language models, before version 0.9.0. When a new prompt is processed and the PageAttention mechanism finds a matching prefix chunk, prefill is faster, which shows up in TTFT (Time to First Token). These timing differences are large enough to be recognized and exploited.

Mitigation

Fixed in version 0.9.0.

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

• vllmPyPILLM dependency since 2023-08-25 · 15 tracked dependents

Topics

• Inference infrastructure

Related items

• MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
• MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
• HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
• InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
• MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online