CVE-2026-133503 json
ModelCloud GPTQModel Adapter Resolution Pipeline remote.py gptqmodel.adapter.remote.resolve_path input validation
published yesterday modified yesterday also EUVD-2026-131272
- cvss
- 5.3
- version 4.0, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.7%
- EPSS 0.7% chance of exploitation in 30 days, percentile 52%
- public exploits
- 0
- none known
Summary
A security vulnerability has been detected in ModelCloud GPTQModel up to 7.6.0. Affected by this vulnerability is the function gptqmodel.adapter.remote.resolve_path of the file gptqmodel/adapter/remote.py of the component Adapter Resolution Pipeline. Such manipulation of the argument adapter.path leads to improper input validation. The attack may be launched remotely. The exploit has been disclosed publicly and may be used. Upgrading to version 7.7.0 addresses this issue. The name of the patch is ed99ac8d59940bf27bb24ce2e80002ae9e44469f. It is advisable to upgrade the affected component.
Patch / fix
- ModelCloud GPTQModel 7.7.0
Is CVE-2026-133503 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- partial
- Assessed
- yesterday
Exploit prediction
0.67% chance of exploitation in the next 30 days, higher than 52% of all scored CVEs (FIRST EPSS, 2026-11-21).
Exploits and checks
- github.com https://github.com/user-attachments/files/33754994/poc.zip referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 5.3 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P |
| CNA | 3.1 | 6.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:L/E:P/RL:O/RC:C |
| CNA | 3.0 | 6.3 | CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:L/E:P/RL:O/RC:C |
| CNA | 2.0 | 7.5 | AV:N/AC:L/Au:N/C:P/I:P/A:P/E:POC/RL:OF/RC:C |
Inferred packages
No advisory lists a package for this vulnerability yet. The CVE names these as products and links their GitHub repository, and the package registry names the same repository, so they are probably the affected packages. Low confidence: the versions are the CVE’s own for the product, and a stack check reports the package as unchecked when there are none.
| ecosystem | package | repository | affected |
|---|---|---|---|
| pypi | gptqmodel | modelcloud/gptqmodel | 7.0 7.1 7.2 7.3 7.4 7.5 7.6.0 |
Affected products
- ModelCloud GPTQModel
Classification
- Weakness
-
- CWE-20 Improper Input Validation
References
-
github.com
/ModelCloud/GPTQModel/pull/3409
issue-tracking, patch
-
github.com
/ModelCloud/GPTQModel/commit/ed99ac8d59940bf27bb24ce2e80002ae9e44469f
patch
-
github.com
/ModelCloud/GPTQModel/releases/tag/v7.7.0
patch
-
github.com
/user-attachments/files/33754994/poc.zip
exploit
-
vuldb.com
/vuln/440925
vdb-entry, technical-description
-
vuldb.com
/vuln/440925/cti
signature, permissions-required
-
vuldb.com
/cve/CVE-2026-133503
third-party-advisory
-
vuldb.com
/submit/1049320
third-party-advisory
-
github.com
/ModelCloud/GPTQModel/issues/3407
issue-tracking
-
github.com
/ModelCloud/GPTQModel/
product
Sources
- CVE List CVE-2026-133503
- NVD CVE-2026-133503
Fencer Intel 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.