Intel

AIKIDO-2026-96665

ouroboros-ai is vulnerable to Authentication Bypass

Authentication Bypass Pre-CVE
Found by Aikido Intel before public disclosure or CVE publication.
Published 2 days ago

81

High Risk

This Affects:

PYTHONouroboros-ai
0.13.3 - 0.51.1
Fixed in 0.51.2
Are you affected? Scan for Free

TL;DR

The MCP server exposes network transports (sse and streamable-http) that bind to a caller-supplied host and port. When bound beyond loopback, the server accepts requests without any authentication and lets callers invoke privileged tools such as ouroboros_execute_seed. That tool runs caller-supplied seed YAML with the agent runtime's local file and shell authority, so any reachable client can execute arbitrary agent workflows. The fix refuses non-loopback binds unless an auth token and an explicit remote-exposure flag are set, and adds Host/Origin validation and workspace-root confinement.

Who does this affect?

You are affected if you are using a version that falls within the vulnerable range and you run the MCP server on an sse or streamable-http transport bound to a non-loopback address reachable by untrusted clients.

Background info

ouroboros-ai is vulnerable to Authentication Bypass in versions 0.13.3 - 0.51.1.

How to fix this

Upgrade the ouroboros-ai library to the patch version.

Are You Affected?

Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.

Free. No credit card required.

Aikido Platform