Medium severity · published Aug 13, 2026
CVE-2026-73558
vLLM: Cross-User Data Leak Vulnerability
5.3
CVSS
0.4%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N
Attack vector
Network
Complexity
High
Privileges
None
User interaction
Required
Confidentiality
High
Integrity
None
Availability
None
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.4% · higher than 35% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
vllm · vllm-project
< 0.27.0 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-73558
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-73558
Patch
https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924
Issue Tracking
https://github.com/vllm-project/vllm/issues/42860
Issue Tracking
https://github.com/vllm-project/vllm/pull/49660
Release Notes
https://github.com/vllm-project/vllm/releases/tag/v0.27.0
Exploit
https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5
More from vllm
9.8
CVE-2026-115915
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
9.8
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
9.8
CVE-2024-9053
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints