AI agent vulnerability · vLLM

GHSA-78fp-cf4h-g36p: Duplicate Advisory: vLLM introduced enhanced protection for CVE-2025-62164

highCVSS 4.0 8.7 · 3.1 8.8

This advisory was withdrawn on Sep 11, 2026. The publisher no longer considers it a valid vulnerability.

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mcmc-2m55-j8jj. This link is maintained to preserve external references. Original Description vLLM versions = 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing.

Published Jun 20, 2026 · Updated Sep 11, 2026

Affected packages

vllm

Ecosystem: PyPI
Affected: >= 0.10.2, < 0.13.0
Fixed in: 0.13.0
Check: pip show vllm

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Duplicate Advisory

This advisory has been withdrawn because it is a duplicate of GHSA-mcmc-2m55-j8jj. This link is maintained to preserve external references.

Original Description

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.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More vLLM vulnerabilities

All vLLM entries