SEPTEMBER 19, 2026
Live Feed
Back to database
Case File

CVE-2026-61437

HIGH · CVSS 7.8 EPSS 0.13% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-07-10 · Last synced 2026-08-09

CyberRota Analysis

AI-Generated

The PraisonAI pip package prior to version 1.6.78 is vulnerable to an unsafe dynamic module loading issue, allowing an attacker to execute arbitrary Python code by controlling a workflow file and its associated tools.py. This vulnerability arises when the framework imports the tools.py file without proper sandboxing, disregarding security environment variables. Organizations using this package, particularly those implementing workflow automation, should prioritize patching to mitigate the risk of code execution under the workflow runner's privileges.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

GitHub PoC Links

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-61437
Severity
HIGH
CVSS
7.8
EPSS
0.13%

Original NVD Description

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.