Advisory

GHSA-mcmc-2m55-j8jj

Also known as: CVE-2026-56340, PYSEC-2026-250

Summary

vLLM introduced enhanced protection for CVE-2025-62164

Details

Summary
The fix here for CVE-2025-62164 is not sufficient. The fix only disables prompt embeds by default rather than addressing the root cause, so the DoS vulnerability remains when the feature is enabled.

Details
vLLM's pending change attempts to fix the root cause, which is the missing sparse tensor validation. PyTorch (~v2.0) disables sparse tensor validation (specifically, sparse tensor invariants checks) by default for performance reasons. vLLM is adding the sparse tensor validation to ensure indices are valid, non-negative, and within bounds. These checks help catch malformed tensors.

PoC
NA

Impact
Current fix only added a flag to disable/enable prompt embeds, so by default, prompt embeds feature is disabled in vLLM, which stops DoS attacks through the embeddings. However, It doesn’t address the problem when the flag is enabled and there is still potential for DoS attacks.

Changes

  • https://github.com/vllm-project/vllm/pull/30649

Severity

High Basis: The source's own band: HIGH

Dates

Published
2026-01-08 21:47 UTC
Modified
2026-09-11 19:30 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: GitHub Advisory Database (reviewed advisories) · CC BY 4.0

Sources & licences