Skip to content
Fencer Vulns
high 7.6

CVE-2025-61784 json

LLaMA Factory's Chat API has Critical SSRF and LFI Vulnerabilities

published 2025-10-07 13 mo ago modified 2026-10-08 31 d ago also EUVD-2025-31881 , GHSA-527m-2xhr-j27g , PYSEC-2026-1573

cvss
7.6
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 32%
public exploits
0
none known

Summary

LLaMA-Factory is a tuning library for large language models. Prior to version 0.9.4, a Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server's filesystem. The vulnerability exists in the `_process_request` function within `src/llamafactory/api/chat.py.` This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs. The function checks if the provided URL is a base64 data URI or a local file path (`os.path.isfile`). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using `requests.get(url, stream=True).raw` without any validation or sanitization of the URL. Version 0.9.4 fixes the underlying issue.

Patch / fix

  • pypi llamafactory 0.9.4
  • hiyouga llama-factory 0.9.4

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
13 mo ago

Exploit prediction

0.38% chance of exploitation in the next 30 days, higher than 32% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 7.6 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L
GitHub 3.1 7.6 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L
NVD 3.1 8.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
OSV 3.1 7.6 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L

Affected packages

ecosystem package affected fixed in
pypi llamafactory
<0.9.4
0.9.4

Affected products

  • hiyouga LLaMA-Factory

Classification

Weakness
  • CWE-22 Improper Limitation of a Pathname to a Restricted Directory
  • CWE-918 Server-Side Request Forgery

References

Sources

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.

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