PraisonAI's MCP integration prior to version 4.5.128 allows spawning background servers using user-supplied command strings executed through Python's subprocess module. By default, the subprocess inherits all environment variables from the parent process, including sensitive information such as API keys, authentication tokens, and database credentials. This behavior creates a risk when untrusted or third-party commands are executed, as they gain access to these sensitive environment variables. The vulnerability can lead to exposure of sensitive information and potential supply chain attacks via silent exfiltration of secrets. The issue is resolved in PraisonAI version 4.5.128.

The vulnerability exposes sensitive environment variables to subprocesses spawned by user-supplied commands, potentially leaking API keys, authentication tokens, and database credentials. This exposure can lead to unauthorized access to sensitive information and enable supply chain attacks through compromised or malicious third-party packages. The CVSS score of 5.5 reflects a medium severity impact, primarily confidentiality loss without direct integrity or availability impact.

A fix for this vulnerability is available in PraisonAI version 4.5.128. Users should upgrade to version 4.5.128 or later to remediate the issue. Until the upgrade is applied, avoid executing untrusted or third-party MCP commands that could inherit sensitive environment variables. Patch status is not explicitly stated beyond the version fix; therefore, verify the vendor advisory for the latest remediation guidance.