CVE-2026-55529

published 25 Aug 2026 · updated 27 Aug 2026

PraisonAI: Origin validation bypass in MCP HTTP Stream transport allows browser-mediated unauthenticated tool execution on local MCP server

6.9MediumCVSS 6.9EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. No fixed version is recorded.

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream _validate_origin method accepts request_origin.startswith(allowed), so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit tools/call requests to the local MCP server and execute exposed tools. This issue is fixed in version 4.6.58.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
MervinPraison<4.6.58

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-55529 severity on Zeptric[![CVE-2026-55529](https://zeptric.io/badge/cve/CVE-2026-55529.svg)](https://zeptric.io/cve/CVE-2026-55529)