Advisory

PYSEC-2026-4185

Also known as: CVE-2026-100652, GHSA-qff2-492f-9fm4

Summary

The record has no summary.

Details

vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.

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
2026-09-26 14:16 UTC
Modified
2026-10-07 10:00 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0.22.0, fixed 0.24.0 (ecosystem)

Fixed versions

0.24.0

Fix

  • Fixed version 0.24.0
    pip install --upgrade vllm==0.24.0

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