CVE-2026-44336

CriticalCVSS 9.6/10Last modified Jun 17, 2026

Description

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 background Python service. This issue has been patched in version 4.6.34.

Metrics

CVSS 3.1 9.6/10CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Weakness enumeration

Affected software

No affected versions have been published.

Timeline

Published
May 8, 2026
Last modified
Jun 17, 2026
NVD status
Modified

Related CVEs from 2026

CVE-2026-443376.3PraisonAI is a multi-agent teams system. From version 2.4.1 to before version 4.6.34, PraisonAI exposes optional SQL/CQL-backed knowledge-stCVE-2026-443387.3PraisonAI is a multi-agent teams system. From version 2.5.6 to before version 4.6.34, PraisonAI ships a legacy Flask API server with authentCVE-2026-443398.6PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unreCVE-2026-44348.1Improper certificate validation in the PAM propagation WinRM connections allows a network attacker to perform a man-in-the-middle attack viCVE-2026-443407.5PraisonAI is a multi-agent teams system. Prior to version 4.6.37, the _safe_extractall helper that all recipe pull, recipe publish, and reciCVE-2026-443415.3GoJobs is a REST API for a Job Board platform. The application exposes a job retrieval endpoint that allows unauthenticated users to access CVE-2026-443425.3New API is a large language mode (LLM) gateway and artificial intelligence (AI) asset management system. Prior to 0.12.0-alpha.1, the email CVE-2026-443439.8WGDashboard is a dashboard for WireGuard VPN. Prior to 4.3.2, there are critical vulnerabilities affecting WGDashboard that, if exploited, cCVE-2026-443458.8BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.39, src/bentoml/_intCVE-2026-443468.8BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.39, a malicious bentCVE-2026-443476.5Warpgate is an open source SSH, HTTPS and MySQL bastion host for Linux. Prior to 0.23.3, the SSO flow does not validate the state parameter,CVE-2026-443482.5PoDoFo is a C++17 PDF manipulation library. From 1.0.0 to before 1.0.4, a double-free vulnerability exists in compute_hash_to_sign() in src/
CVE-2026-44336: Critical severity, CVSS 9.6 | Vulnix