CVE-2026-61437PraisonAI before 1.6.78 Remote Code Execution via tools.py
Descripción
PraisonAI (pip package praisonaiagents) before 1.6.78 contains an unsafe dynamic module loading vulnerability in AgentFlow._resolve_pydantic_class (src/praisonai-agents/praisonaiagents/workflows/workflows.py). When a workflow step uses a string output_pydantic reference, the framework locates and imports a sibling tools.py from the workflow file's directory via importlib exec_module without sandboxing, ignoring the PRAISONAI_ALLOW_*_TOOLS environment variables. An attacker who controls a workflow file and its sibling tools.py can execute arbitrary Python code with the workflow runner's privileges when the workflow is executed via WorkflowManager or after load_yaml.
Datos: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Se publican tal como los indican las fuentes, en inglés.
Productos y versiones afectados
| Fabricante | Producto | Versiones | |
|---|---|---|---|
| MervinPraison | PraisonAI | < 1.6.78, fixed 1.6.78 | |
| praison | praisonai | < 1.6.78 |
Referencias y parches
- GitHub Security Advisory (GHSA-4gfv-wg42-7jw5) vendor-advisory
- VulnCheck Advisory: PraisonAI before 1.6.78 Remote Code Execution via tools.py third-party-advisory