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.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Privileges Required
None
No privileges needed
User Interaction
Required
User action required
Impact Assessment
Confidentiality
Low
Partial data leak
Integrity
High
Complete data modification
Availability
Low
Partial disruption
CVSS Vector v3.1
Weakness Type (CWE)
References 3
https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828…
security-advisories@github.com
https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58
security-advisories@github.com
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pvph-5j39-v…
security-advisories@github.com