Permissive Cross-domain Policy with Untrusted Domains Affecting praisonai package, versions [,4.5.125)

PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration.

Affected versions of this package are vulnerable to Permissive Cross-domain Policy with Untrusted Domains in the POST /agui endpoint due to the absence of authentication and the use of a hardcoded Access-Control-Allow-Origin: * header. An attacker can execute arbitrary agent actions and exfiltrate sensitive data by luring a victim to visit a malicious website, which then sends crafted cross-origin requests to a locally running server.

Note: This is only exploitable if the AGUI server is running locally and the victim visits an attacker-controlled website.

• GitHub Advisory
• GitHub Commit
• Vulnerable Code
• Vulnerable Code