Advisory

PYSEC-2026-250

Also known as: CVE-2026-56340, GHSA-mcmc-2m55-j8jj

Summary

The record has no summary.

Details

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

Severity

High Basis: CVSS v3 score 7.5, vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Dates

Published
2026-06-20 19:16 UTC
Modified
2026-06-27 11:15 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0.10.2, fixed 0.13.0 (ecosystem)

Fixed versions

0.13.0

Fix

  • Fixed version 0.13.0
    pip install --upgrade vllm==0.13.0

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences