CVE-2026-133612SqueezeAILab SqueezeLLM out-of-bounds write
CVE-2026-133612 is a out-of-bounds write in SqueezeAILab SqueezeLLM, rated low (2.0 on CVSS 4.0).
Why this priority: Low severity, with no exploitation signal.
Published · Updated · NVD status: Deferred
What it is
Code writes past the end of a buffer, corrupting memory in ways an attacker can often turn into code execution. Code reads or writes outside the memory it was given, which can corrupt the process.
How it is reached
An attacker can exploit it over the network, with an ordinary user account, but someone has to act first, such as opening a file or following a link.
What an attacker gains
The direct impact is limited: partial access to data or a partial outage. In practice, this kind of flaw lets an attacker crash the process, read memory, or in the worst case run code.
Is it being exploited?
CISA's SSVC assessment notes a public proof of concept.
What to do
- No fixed version is listed yet. Find every place SqueezeAILab SqueezeLLM runs, watch the references for a fix, and plan a replacement if it is no longer supported.
- While there is no fix, review who holds accounts that can reach it.
- Warn the people who use it, and filter files and links on the way in.
Description from NVD
A weakness has been identified in SqueezeAILab SqueezeLLM up to a5fd71f353bf569feb7b55737c1c1493e78e8f31. This vulnerability affects the function vecquant4matmul_spmv_hybrid_nuq_perchannel of the file quant_cuda_kernel.cu of the component CUDA Matvec Kernel. Executing a manipulation of the argument full_row_indices can lead to out-of-bounds write. The attack can be launched remotely. The exploit has been made available to the public and could be used for attacks. This product does not use versioning. This is why information about affected and unaffected releases are unavailable. The project was informed of the problem early through an issue report but has not responded yet.
What this means for your architecture.
A CVE names a product. Whether it matters depends on where that product sits in your systems: what reaches it, which trust boundary it guards and what it can reach once compromised. Veriom maps your components, their relationships and your trust boundaries from your code, cloud and delivery evidence, so you can see where a component like this sits. The radar itself does not look at your systems.
Components it touches
- Native code: operating systems, browsers and firmware. The flaw sits wherever native code reads untrusted data.
- Network appliances and media or file parsers. The flaw sits wherever native code reads untrusted data.
Trust boundaries in play
- Authenticated network access. An account is needed, so exposure follows who can sign in: customers, partners or staff.
- People who open files and links. Mail, chat and browsers are the delivery path.
- Wherever native code reads untrusted data. An attacker who crosses it can crash the process, read memory, or in the worst case run code.
Questions to answer about your own systems
- Where does SqueezeAILab SqueezeLLM run in your systems, and at which version?
- Which of those instances can be reached from the internet or partner networks?
- What can it reach once compromised: which data stores, secrets and services?
14-day free trial
Understand how your systems connect.
See your services, dependencies and trust boundaries in one place, with evidence from your connected environment.
Sources
- CVE records and CVSS scores from the NVD CVE API. This product uses the NVD API but is not endorsed or certified by the NVD.
- Exploitation status from CISA’s Known Exploited Vulnerabilities catalog.
- Exploit likelihood from FIRST’s Exploit Prediction Scoring System (EPSS), refreshed daily.
- Explanations are written by Veriom from fixed templates over each record’s data, not by a person reviewing each CVE. Descriptions are quoted from the records as published.