Detections
Analytics
CVE-2026-55532
high
Description
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.
References
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pvph-5j39-v8qc
https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58
https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1