CVE-2026-61447

published 11 Jul 2026 · updated 13 Jul 2026

PraisonAI before 1.6.78 Remote Code Execution via CodeAgent

10.0CriticalCVSS 10.0EPSS 15%1 public exploits

A public exploit exists; no exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 15%. Fixed in 1.6.78.

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
MervinPraison<1.6.781.6.78

Exploit evidence

1 public sources

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-61447 severity on Zeptric[![CVE-2026-61447](https://zeptric.io/badge/cve/CVE-2026-61447.svg)](https://zeptric.io/cve/CVE-2026-61447)