Skip to content
Fencer Intel
high 8.3

CVE-2025-53002 json

LLaMA-Factory Remote Code Execution (RCE) Vulnerability

published last yr. modified 4mo ago also EUVD-2025-19200 , GHSA-xj56-p8mm-qmxj , PYSEC-2026-1576

cvss
8.3
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
1.3%
EPSS 1.3% chance of exploitation in 30 days, percentile 70%
public exploits
0
none known

Summary

LLaMA-Factory is a tuning library for large language models. A remote code execution vulnerability was discovered in LLaMA-Factory versions up to and including 0.9.3 during the LLaMA-Factory training process. This vulnerability arises because the `vhead_file` is loaded without proper safeguards, allowing malicious attackers to execute arbitrary malicious code on the host system simply by passing a malicious `Checkpoint path` parameter through the `WebUI` interface. The attack is stealthy, as the victim remains unaware of the exploitation. The root cause is that the `vhead_file` argument is loaded without the secure parameter `weights_only=True`. Version 0.9.4 contains a fix for the issue.

Patch / fix

  • hiyouga llama-factory 0.9.4

Is CVE-2025-53002 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
last yr.

Exploit prediction

1.27% chance of exploitation in the next 30 days, higher than 70% of all scored CVEs (FIRST EPSS, 2026-11-09).

Exploits and checks

  • github.com https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-xj56-p8mm-qmxj referenced PoC, tagged "exploit" by a source, unverified
  • drive.google.com https://drive.google.com/file/d/1AddKm2mllsXfuvL4Tvbn_WJdjEOYXx4y/view?usp=sharing referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 8.3 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:H
GitHub 3.1 8.3 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:H
NVD 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
OSV 3.1 8.3 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:H

Affected packages

ecosystem package affected fixed in
pypi llamafactory
<=0.9.3
 no fix listed

Affected products

  • hiyouga LLaMA-Factory

Classification

Weakness
  • CWE-94 Improper Control of Generation of Code
  • CWE-502 Deserialization of Untrusted Data

References

Sources

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.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.