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.
References3
Metrics
- CVSS 3.1
-
7.6
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L - EPSS — exploit probability
- 0% percentile: 9 · as of 9 November 2026
- CWE
- CWE-346CWE-352
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.