CVE-2026-44336
CriticalSummary
PraisonAI prior to version 4.6.34 has a vulnerability in the MCP server that allows an attacker to write files outside the rules directory. This can lead to arbitrary code execution in the user's context.
Risk Assessment
The organization is at risk of unauthorized access and execution of malicious code, potentially leading to serious security breaches.
Recommendation
It is recommended to update PraisonAI to version 4.6.34 or later and implement appropriate access controls for user directories.
Original NVD description (English source)
PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a path or filename string from MCP tools/call arguments and joins it onto ~/.praison/rules/ (or, for workflow.show, accepts an absolute path) with no containment check. The JSON-RPC dispatcher passes params["arguments"] blind to each handler via **kwargs without validating against the advertised input schema. By setting rule_name="../../<some-path>" an attacker walks out of the rules directory and writes any file the running user can write. Dropping a Python .pth file into the user site-packages directory escalates this primitive to arbitrary code execution in any subsequent Python process the user spawns — the next praisonai CLI invocation, an IDE script run, the user's python REPL, or any back