# CVE-2026-81315: ash-project ash_ai origin validation bypass in MCP server

Source: https://junglewise.ai/threats/cve-2026-81315-ash-project-ash-ai-origin-validation-bypass-in-mcp-server  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-08-31. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2026-81315 · Severity: info · Published 2026-08-31

ash_ai is a library that provides an MCP (Model Context Protocol) server for AI integration. A flaw in its origin validation allows attackers to bypass DNS-rebinding protection through malicious web pages, enabling unauthorized cross-site requests to users' local MCP servers with the user's credentials. This could allow attackers to manipulate local AI operations or extract sensitive information.

Technologies: [Ash-Project Ash Ai](https://junglewise.ai/threats/technologies/ash-ai). Vendors: [Ash-Project](https://junglewise.ai/threats/vendors/ash-project).

## Quick answers

**Is CVE-2026-81315 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-81315 being exploited in the wild.

**How severe is CVE-2026-81315?** Informational severity, published 31 August 2026.

**Which products and versions are affected?** Ash-Project Ash Ai 0.8.0 before 1.0.0.

**Is there a fix for CVE-2026-81315?** No fixed version is recorded yet. Check the vendor's advisory in the references below. 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-2026-81315 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-81315?** Check whether you run Ash-Project Ash Ai 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.

## Technical details

The vulnerability is an origin validation error in AshAi.Mcp.Server's origin_allowed?/3 function. With default configuration (allowed_origins: nil), the check compares uri.host against conn.host and validates the forwarded scheme is https, but both values are attacker-controlled: the Host header and raw X-Forwarded-Proto header are used without verifying a trusted proxy. Under DNS rebinding, an attacker's origin and matching host are sent by the browser, and JavaScript can set X-Forwarded-Proto: https, causing the validation to pass even without actual TLS or proxy involvement. The fix restricts default origins to localhost only, requiring explicit allowlist configuration for other origins.

## Affected products

- ash-project ash_ai 0.8.0 before 1.0.0

## Timeline

- 2026-08-31: disclosed

## References

- [https://repo.hex.pm/](https://repo.hex.pm/)
- [https://github.com/](https://github.com/)

## Related threats

- [ash-project ash_ai sensitive information disclosure in error messages](https://junglewise.ai/threats/cve-2026-119613-generation-of-error-message-containing-sensitive-information)
- [ash-project ash_ai information disclosure in error messages](https://junglewise.ai/threats/cve-2026-82580-ash-project-ash-ai-information-disclosure-in-error-messages)
- [Ash AI tool loop infinite loop via prompt injection](https://junglewise.ai/threats/cve-2026-82579-ash-ai-tool-loop-infinite-loop-via-prompt-injection)
- [ash-project ash_ai authorization bypass in identity-configured tools](https://junglewise.ai/threats/cve-2026-82564-ash-project-ash-ai-authorization-bypass-in-identity-configured)
- [ash-project ash_ai sensitive information disclosure in error messages](https://junglewise.ai/threats/cve-2026-75760-ash-project-ash-ai-sensitive-information-disclosure-in-error)