CVE-2026-55529 - 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. - 漏洞详情

漏洞编号：CVE-2026-55529

风险等级：中危

漏洞来源：CVE

CVE 编号：CVE-2026-55529

CNNVD 编号：-

厂商/产品：- / -

影响范围：-

CWE：CWE-306

发布/更新时间：2026-08-25 / 2026-08-27

漏洞描述

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.

漏洞描述

相关链接

相关漏洞