# CVE-2026-115813: Amazon Web Services Multi Model Server path traversal and SSRF

Source: https://junglewise.ai/threats/cve-2026-115812-and-issue-in-amazon-web-services-multi-model-server  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-23. Updated: 2026-10-23  
License: CC BY 4.0 with a link back

CVE-2026-115813 · Severity: critical · CVSS 9.8 · Published 2026-10-23

Amazon Web Services Multi Model Server is an open-source tool for serving machine learning models for inference that has reached end of life. Two vulnerabilities in its unauthenticated management interface could allow attackers to execute code on the server or redirect it to make requests to unintended network destinations. Since the product is no longer maintained and no fixes are available, users must migrate to a supported alternative.

Technologies: [Amazon AWS](https://junglewise.ai/threats/technologies/aws). Vendors: [Amazon](https://junglewise.ai/threats/vendors/amazon), [Amazon Web Services](https://junglewise.ai/threats/vendors/amazon-web-services).

## Quick answers

**Is CVE-2026-115813 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-115813 being exploited in the wild.

**How severe is CVE-2026-115813?** Critical severity, with a CVSS score of 9.8, published 23 October 2026.

**Which products and versions are affected?** Amazon Web Services Multi Model Server <=1.1.11 (all released versions).

**Is there a fix for CVE-2026-115813?** No fixed version is recorded yet. Bind the management interface to the loopback address to restrict access to trusted local connections, and do not pass externally supplied URLs to the model-download path. For SageMaker-style deployments where the management interface cannot be moved to loopback, ensure the serving port is reachable only by trusted callers.</anigation>
<parameter name="timeline">[{"kind":"disclosed","at":"2026-10-23"}] If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-115813 attacked?** It is attacked over the network, in a hosted service.

**Am I affected by CVE-2026-115813?** Check whether you run Amazon AWS or Amazon Web Services Multi Model Server at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix


Bind the management interface to the loopback address to restrict access to trusted local connections, and do not pass externally supplied URLs to the model-download path. For SageMaker-style deployments where the management interface cannot be moved to loopback, ensure the serving port is reachable only by trusted callers.</anigation>
<parameter name="timeline">[{"kind":"disclosed","at":"2026-10-23"}]

## Technical details

CVE-2026-115812 is a path traversal flaw in model archive extraction that allows crafted archives to write files outside the intended directory, leading to code execution with MMS process privileges. CVE-2026-115813 is a server-side request forgery (SSRF) in the model download path that allows the unauthenticated management interface to make requests to attacker-controlled destinations. Both vulnerabilities affect deployments where the management interface is bound to network-accessible addresses.

## Affected products

- Amazon Web Services Multi Model Server <=1.1.11 (all released versions)

## Identifiers

- CVE-2026-115813
- CVE-2026-115812

## References

- [https://aws.amazon.com/security/security-bulletins/rss/2026-148-aws/](https://aws.amazon.com/security/security-bulletins/rss/2026-148-aws/)

## Related threats

- [An untrusted search path issue in Aurora PostgreSQL dialect detection in the AWS Advanced Go Wrapper from release 2026-04-06 (awssql/v2.0.0)](https://junglewise.ai/threats/cve-2026-126793-privilege-escalation-in-aurora-postgresql-dialect-detection-in)
- [AWS SDK for pandas EMR unverified bucket ownership](https://junglewise.ai/threats/cve-2026-127119-unverified-ownership-of-the-default-emr-cluster-log-location-in)
- [Amazon mcp-gateway-registry server-side request forgery in registration API](https://junglewise.ai/threats/cve-2026-125926-server-side-request-forgery-in-the-server-registration-and)
- [Amazon mcp-gateway-registry authorization bypass in management API](https://junglewise.ai/threats/cve-2026-100307-missing-authorization-on-the-external-management-api-in-mcp)
- [AWS Kiro CLI incorrect default permissions on session files](https://junglewise.ai/threats/cve-2026-124848-incorrect-default-permissions-on-session-transcripts-and-prompt)