CVE-2026-55532

published 25 Aug 2026 · updated 25 Aug 2026

PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

7.6HighCVSS 7.6EPSS 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, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests without preflight and invoke tools/call without an API key, including file writes that persist agent instructions. 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-2026-55532 severity on Zeptric[![CVE-2026-55532](https://zeptric.io/badge/cve/CVE-2026-55532.svg)](https://zeptric.io/cve/CVE-2026-55532)