A AegiFlow
HIGHCVSS 8.8EPSS 0.6%

CVE-2026-56340

vLLM introduced enhanced protection for CVE-2025-62164

Published
2026-01-08
Modified
2026-09-11
EPSS percentile
49%
Aliases
GHSA-mcmc-2m55-j8jj
Sources
github-advisory

Summary

### Summary The fix [here](https://github.com/vllm-project/vllm/pull/27204) 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

Affected packages

EcosystemPackageAffected versionsFixed versions
PyPIvllm0.13.0

Remediation: Upgrade to 0.13.0 or later.

References

Includes data from the GitHub Advisory Database, licensed under CC-BY 4.0.

CVE® is a registered trademark of The MITRE Corporation. CVE content reproduced under the CVE Terms of Use; copyright designation © MITRE.

EPSS scores provided by the FIRST.org Exploit Prediction Scoring System.