Vulnerability · Published Aug 13, 2026 · Assigned by GitHub_M

CVE-2026-73558vLLM: Cross-User Data Leak Vulnerability

Medium 5.3

In plain English

A medium-severity integer overflow in vllm from vllm-project. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 36% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)5.3Medium

Exploit odds (30 days)0.4%top 64.1% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	vllm	0.27.0	GHSA-7m6h-x95x-82q5
PyPI	vllm	0.27.0	PYSEC-2026-3935

Affected products (as reported)

Vendor	Product	Versions
vllm-project	vllm	< 0.27.0

Weakness: CWE-190 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N

References

https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5 x_refsource_CONFIRM
https://github.com/vllm-project/vllm/issues/42860 x_refsource_MISC
https://github.com/vllm-project/vllm/pull/49660 x_refsource_MISC
https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924 x_refsource_MISC
https://github.com/vllm-project/vllm/releases/tag/v0.27.0 x_refsource_MISC