Skip to content
Fencer Vulns
medium 5.3

CVE-2025-66908 json

Turms AI-Serving module v0.10.0-SNAPSHOT and earlier contains an improper file type validation vulnerability in the OCR image upload functi…

published 2025-12-19 10 mo ago modified 2026-10-13 27 d ago also EUVD-2025-204533

cvss
5.3
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 38%
public exploits
0
none known

Summary

Turms AI-Serving module v0.10.0-SNAPSHOT and earlier contains an improper file type validation vulnerability in the OCR image upload functionality. The OcrController in turms-ai-serving/src/main/java/im/turms/ai/domain/ocr/controller/OcrController.java uses the @FormData(contentType = MediaTypeConst.IMAGE) annotation to restrict uploads to image files, but this constraint is not properly enforced. The system relies solely on client-provided Content-Type headers and file extensions without validating actual file content using magic bytes (file signatures). An attacker can upload arbitrary file types including executables, scripts, HTML, or web shells by setting the Content-Type header to "image/*" or using an image file extension. This bypass enables potential server-side code execution, stored XSS, or information disclosure depending on how uploaded files are processed and served.

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
partial
Assessed
10 mo ago

Exploit prediction

0.44% chance of exploitation in the next 30 days, higher than 38% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/Xzzz111/public_cve_report/blob/main/CVE-2025-66908_report.md referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CISA ADP 3.1 5.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
CNA 3.1 5.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Classification

Weakness
  • CWE-434 Unrestricted Upload of File with Dangerous Type

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.