SqueezeAILab SqueezeLLM up to a5fd71f353bf569feb7b55737c1c1493e78e8f31 CUDA Matvec Kernel quant_cuda_kernel.cu vecquant4matmul_spmv_hybrid_nuq_perchannel full_row_indices out-of-bounds write
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 5.2 | $0-$5k | 0.41+ |
Summary
A vulnerability was found in SqueezeAILab SqueezeLLM up to a5fd71f353bf569feb7b55737c1c1493e78e8f31. It has been rated as problematic. This issue affects the function vecquant4matmul_spmv_hybrid_nuq_perchannel of the file quant_cuda_kernel.cu of the component CUDA Matvec Kernel. The manipulation of the argument full_row_indices leads to out-of-bounds write.
This vulnerability is listed as CVE-2026-133612. The attack may be initiated remotely. In addition, an exploit is available.
This product uses a rolling release model to deliver continuous updates. As a result, specific version information for affected or updated releases is not available.
The project was informed of the problem early through an issue report but has not responded yet.
Details
A vulnerability was found in SqueezeAILab SqueezeLLM up to a5fd71f353bf569feb7b55737c1c1493e78e8f31 and classified as problematic. This issue affects the function vecquant4matmul_spmv_hybrid_nuq_perchannel of the file quant_cuda_kernel.cu of the component CUDA Matvec Kernel. The manipulation of the argument full_row_indices with an unknown input leads to a out-of-bounds write vulnerability. Using CWE to declare the problem leads to CWE-787. The product writes data past the end, or before the beginning, of the intended buffer. Impacted is confidentiality, integrity, and availability.
It is possible to read the advisory at github.com. The identification of this vulnerability is CVE-2026-133612. The exploitation is known to be easy. The attack may be initiated remotely. It demands that the victim is doing some kind of user interaction. Technical details as well as a public exploit are known.
The exploit is available at github.com. It is declared as proof-of-concept. The project was informed of the problem early through an issue report but has not responded yet.
There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.
Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.
Product
Vendor
Name
Version
Website
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 5.5VulDB Meta Temp Score: 5.2
VulDB Base Score: 5.5
VulDB Temp Score: 5.2
VulDB Vector: 🔒
VulDB Reliability: 🔍
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: Out-of-bounds writeCWE: CWE-787 / CWE-119
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Access: Public
Status: Proof-of-Concept
Download: 🔒
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: no mitigation knownStatus: 🔍
0-Day Time: 🔒
Timeline
11/20/2026 Advisory disclosed11/20/2026 VulDB entry created
11/20/2026 VulDB entry last update
Sources
Product: github.comAdvisory: 77
Status: Confirmed
CNA: VulDB
CVE: CVE-2026-133612 (🔒)
GCVE (CVE): GCVE-0-2026-133612
GCVE (VulDB): GCVE-100-441203
scip Labs: https://www.scip.ch/en/?labs.20161013
Entry
Created: 11/20/2026 08:28Changes: 11/20/2026 08:28 (60)
Complete: 🔍
Submitter: m00dy
Cache ID: 216::103
Submit
Accepted
- Submit #1050821: SqueezeAILab SqueezeLLM main Out-of-bounds write (by m00dy)
Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.
No comments yet. Languages: en.
Please log in to comment.