CVE-2026-55532
Published:August 25, 2026
Updated:September 24, 2026
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.
Affected Packages
https://github.com/MervinPraison/PraisonAI.git (GITHUB):
Affected version(s) >=v3.0.0 <v4.6.58Fix Suggestion:
Update to version v4.6.58praisonai (PYTHON):
Affected version(s) >=0.0.1 <4.6.58Fix Suggestion:
Update to version 4.6.58Related Resources (6)
Do you need more information?
Contact UsCVSS v4
Base Score:
7.2
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
PASSIVE
Vulnerable System Confidentiality
LOW
Vulnerable System Integrity
HIGH
Vulnerable System Availability
LOW
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
7.6
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
REQUIRED
Scope
UNCHANGED
Confidentiality
LOW
Integrity
HIGH
Availability
LOW
EPSS
Base Score:
0.13