CVE-2026-61437

published 10 Jul 2026 · updated 14 Jul 2026

PraisonAI before 1.6.78 Remote Code Execution via tools.py

7.8HighCVSS 7.8EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in 1.6.78.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
MervinPraison<1.6.781.6.78

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-61437 severity on Zeptric[![CVE-2026-61437](https://zeptric.io/badge/cve/CVE-2026-61437.svg)](https://zeptric.io/cve/CVE-2026-61437)