CVE-2026-73558 json
vLLM: Cross-User Data Leak Vulnerability
published 2026-08-13 2 mo ago modified 2026-09-28 41 d ago also EUVD-2026-58066 , GHSA-7m6h-x95x-82q5 , PYSEC-2026-3935
- cvss
- 5.3
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.4%
- EPSS 0.4% chance of exploitation in 30 days, percentile 35%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
- pypi vllm 0.27.0
- vllm-project vllm 0.27.0
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-73558 updated cvss 5.3
vllm: vLLM: Cross-User Data Leakage via Integer Overflow
-
Red Hat AI Inference Server rhaii/vllm-tpu-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, rhaiis/vllm-cuda-rhel9, rhaiis/vllm-rocm-rhel9, rhaii/vllm-neuron-rhel9, +2 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-gaudi-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-llm-d-kv-cache-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-storage-initializer-rhel9affected: no fix available “Fix deferred”
-
Red Hat AI Inference Server 3.5 rhaii/vllm-cpu-rhel9 1791473614, rhaii/vllm-cuda-rhel9 1791473631, rhaii/vllm-rocm-rhel9 1791425869, rhaii/vllm-gaudi-rhel9 1791427182, rhaii/vllm-spyre-rhel9 1791818357fixed: vendor fix RHSA-2026:82415
-
Red Hat Enterprise Linux AI 3.5 rhelai3/bootc-cuda-rhel9 1793135861, rhelai3/bootc-rocm-rhel9 1793135863, rhelai3/bootc-aws-cuda-rhel9 1793194817, rhelai3/bootc-gcp-cuda-rhel9 1793194815, rhelai3/disk-image-cuda-rhel9 1793206758, rhelai3/bootc-azure-cuda-rhel9 1793194815, +1 morefixed: vendor fix RHSA-2026:92452
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- partial
- Assessed
- 2 mo ago
Exploit prediction
0.41% chance of exploitation in the next 30 days, higher than 35% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 5.3 | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N |
| GitHub | 3.1 | 5.3 | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N |
| OSV | 3.1 | 5.3 | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | vllm | <0.27.0 |
0.27.0 |
Affected products
- vllm-project vllm
Classification
- Weakness
-
- CWE-190 Integer Overflow or Wraparound
References
-
github.com
/vllm-project/vllm/pull/49660
web, issue-tracking, patch
-
github.com
/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924
web, patch
-
github.com
/vllm-project/vllm/issues/42860
web, issue-tracking, patch
-
github.com
/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5
exploit, web, vendor-advisory
-
github.com
/vllm-project/vllm/releases/tag/v0.27.0
web, release-notes
-
nvd.nist.gov
/vuln/detail/CVE-2026-73558
advisory
-
github.com
/vllm-project/vllm
package
-
pypi.org
/project/vllm
package
-
github.com
/advisories/GHSA-7m6h-x95x-82q5
advisory
Sources
- CVE List CVE-2026-73558
- GitHub Advisory GHSA-7m6h-x95x-82q5
- NVD CVE-2026-73558
- OSV PYSEC-2026-3935
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.