CVE-2025-54381
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. In versions 1.4.0 until 1.4.19, the file upload processing system contains an SSRF vulnerability that allows unauthenticated remote attackers to force the server to make arbitrary HTTP requests. The vulnerability stems from the multipart form data and JSON request handlers, which automatically download files from user-provided URLs without validating whether those URLs point to internal network addresses, cloud metadata endpoints, or other restricted resources. The documentation explicitly promotes this URL-based file upload feature, making it an intended design that exposes all deployed services to SSRF attacks by default. Version 1.4.19 contains a patch for the issue.
Scoring
- Severity
- CRITICAL
- CVSS base score
- 9.9
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:L
- EPSS probability
- 14.01%
- CWE
- CWE-918
- Published
- 2025-07-29
- Last modified
- 2026-03-12
Affected products
- bentoml BentoML
Weakness type
Related vulnerabilities
- CVE-2026-88001 — Open WebUI: Server-side fetches reach blocked and internal hosts via unvalidated HTTP redirect targets
- CVE-2026-87999 — Open WebUI: Any authenticated user can reach the Azure platform channel via server-side web fetch
- CVE-2026-87996 — Open WebUI: SSRF into internal services via DNS rebinding in the Playwright web loader
- CVE-2026-19233 — CWE-918: Server-Side Request Forgery (SSRF) vulnerability exists that could cause unauthorized...
- CVE-2026-86771 — Snipe-IT before 8.7.0 Server-Side Request Forgery via employee_num
- CVE-2026-87821 — Lara Dashboard 0.9.2 through 1.3.1 Server-Side Request Forgery in Builder Markdown Fetch
- CVE-2026-79635 — Dell SCG 5.0 Appliance versions prior to 5.36.00.16 and Dell SCG 5.0 Application versions prior to...
- CVE-2026-57866 — Apache Impala: Secrets Exfiltration via SSRF