CVE-2026-7141 json
vLLM KV Block kv_cache_interface.py has_mamba_layers uninitialized resource
published 2026-04-27 6 mo ago modified 2026-09-10 1 mo ago also GHSA-x368-4g9h-fvv4 , PYSEC-2026-2306 , EUVD-2026-25892
- cvss
- 5.6
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.3%
- EPSS 0.3% chance of exploitation in 30 days, percentile 21%
- public exploits
- 0
- none known
Summary
A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The existence of this vulnerability is still disputed at present. The proposed patch did not fix the issue. A 3rd party explains: "The divergence could be explained by a benign and expected vLLM behavior where vLLM server could group concurrent requests together resulting in different input shapes based on varying request arrival time. The differences in grouped input shapes could call different kernels with could produce difference results due to rounding and differences in order of operations. There is an environment variable VLLM_BATCH_INVARIANT=1 for users that desire to have deterministic output with temperature 0.0."
Patch / fix
- pypi vllm 0.19.1
- github.com/AjAnubolu/vllm@1ad6786 commit
- github.com/vllm-project/vllm#39283 pull request
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-2026-7141 updated cvss 5.6
vllm: vllm: Uninitialized resource in KV Block Handler via has_mamba_layers function
-
Red Hat AI Inference Server rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, rhaiis/vllm-cuda-rhel9, rhaiis/vllm-rocm-rhel9, rhaiis/vllm-spyre-rhel9, rhaiis/vllm-neuron-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9, rhelai3/bootc-azure-rocm-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-cuda-rhel9, rhoai/odh-vllm-rocm-rhel9, rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-kserve-controller-rhel9, +1 moreaffected: workaround, no fix available “Fix deferred”
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
- 6 mo ago
Exploit prediction
0.29% chance of exploitation in the next 30 days, higher than 21% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/vllm-project/vllm/issues/39146#issue-4215090365 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 6.3 | CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P |
| CNA | 3.1 | 5.6 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:U/RC:R |
| CNA | 3.0 | 5.6 | CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:U/RC:R |
| CNA | 2.0 | 5.1 | AV:N/AC:H/Au:N/C:P/I:P/A:P/E:POC/RL:U/RC:UR |
| CNA | 4.0 | 2.9 | CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| CNA | 3.1 | 5.6 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L |
| CNA | 2.0 | 5.1 | AV:N/AC:H/Au:N/C:P/I:P/A:P |
| GitHub | 3.1 | 5.6 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | vllm | <0.19.1 |
0.19.1 |
Affected products
- n/a vLLM
Classification
- Weakness
-
- CWE-908 Use of Uninitialized Resource
References
-
github.com
/vllm-project/vllm/pull/39283
web, patch
-
github.com
/AjAnubolu/vllm/commit/1ad67864c0c20f167929e64c875f5c28e1aad9fd
web, patch
-
github.com
/vllm-project/vllm/issues/39146#issue-4215090365
exploit, issue-tracking, web, report
-
vuldb.com
/vuln/359740
vdb-entry, technical-description, web, third-party-advisory, advisory
-
vuldb.com
/vuln/359740/cti
signature, permissions-required, web, report
-
vuldb.com
/cve/CVE-2026-7141
third-party-advisory
-
vuldb.com
/submit/801297
third-party-advisory, web, vdb-entry, advisory
-
github.com
/vllm-project/vllm/issues/39146
issue-tracking, web, report
-
nvd.nist.gov
/vuln/detail/CVE-2026-7141
advisory
-
github.com
/advisories/GHSA-x368-4g9h-fvv4
advisory
Sources
- CVE List CVE-2026-7141
- GitHub Advisory GHSA-x368-4g9h-fvv4
- NVD CVE-2026-7141
- OSV PYSEC-2026-2306
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.