MEDIUM · 6.9

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.ex...

Vulnerability 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.

CVSS Score

6.9

MEDIUM

CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:L/A:N
Attack Vector
NETWORK
Attack Complexity
HIGH
Privileges Required
NONE
User Interaction
REQUIRED
Scope
CHANGED
Confidentiality
HIGH
Integrity
LOW
Availability
NONE

Related Weaknesses (CWE)

References

FAQ

What is CVE-2026-55529?

CVE-2026-55529 is a vulnerability with a CVSS score of 6.9 (MEDIUM). 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.ex...

How severe is CVE-2026-55529?

CVE-2026-55529 has been rated MEDIUM with a CVSS base score of 6.9/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2026-55529?

Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.