CVE-2026-73558
vLLM: Cross-User Data Leak Vulnerability
Description
vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.
INFO
Published Date :
Aug. 13, 2026, 3:20 p.m.
Last Modified :
Aug. 13, 2026, 3:20 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | MEDIUM | [email protected] |
Solution
- Update vLLM to version 0.27.0 or later.
- Apply relevant patches from the vendor.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-73558.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-73558 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-73558
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-73558 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-73558 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Aug. 13, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'vllm-project', 'product': 'vllm', 'versions': [{'status': 'affected', 'version': '< 0.27.0'}]}] Added Description vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0. Added CVSS V3.1 AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N Added CWE CWE-190 Added Reference https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924 Added Reference https://github.com/vllm-project/vllm/issues/42860 Added Reference https://github.com/vllm-project/vllm/pull/49660 Added Reference https://github.com/vllm-project/vllm/releases/tag/v0.27.0 Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5