Description
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.
References4
Metrics
- CVSS 3.1
-
6.9
MEDIUM
Score source: CNA
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:L/A:N - EPSS — exploit probability
- 0% percentile: 7 · as of 9 November 2026
- CWE
- CWE-306CWE-346
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.