CVE-2026-34935

GHSA-9gm9-c8mq-vq7m · published 1 Apr 2026 · updated 16 Nov 2026

PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()

9.8CriticalCVSS 9.8EPSS 1%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 1%. Fixed in praisonai 4.5.69.

PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user. This issue has been patched in version 4.5.69.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
MervinPraison>=4.5.15 <4.5.69
pypi: praisonai>=4.5.15 <4.5.694.5.69

Timeline

Every event on this vulnerability

Related

Other vulnerabilities in praisonai (PyPI), strongest first

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-34935 severity on Zeptric[![CVE-2026-34935](https://zeptric.io/badge/cve/CVE-2026-34935.svg)](https://zeptric.io/cve/CVE-2026-34935)