CVE-2026-61437: PraisonAI unsafe dynamic module loading in AgentFlow

CVE-2026-61437 · Severity: high · CVSS 7.8 · Published 2026-07-10

PraisonAI is an AI agent framework used to automate complex tasks through workflows. A security flaw allows the framework to automatically execute Python code from a file named 'tools.py' if it is located in the same folder as a workflow file being processed. If an attacker can convince a user to run a malicious workflow or place a malicious file in a monitored directory, they can gain full control over the user's system, potentially leading to data theft or unauthorized access to sensitive information.

Technologies: praisonaiagents (PyPI). Vendors: PyPI.

Quick answers

Is CVE-2026-61437 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-61437 being exploited in the wild.
How severe is CVE-2026-61437?
High severity, with a CVSS score of 7.8, published 10 July 2026.
Which products and versions are affected?
praisonaiagents (PyPI) <= 1.6.77, ECOSYSTEM:introduced=0,fixed=1.6.78.
Is there a fix for CVE-2026-61437?
Yes. praisonaiagents (PyPI): upgrade to 1.6.78 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-61437 attacked?
It is attacked with local access, in a software library.
Am I affected by CVE-2026-61437?
Check whether you run praisonaiagents (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

  • praisonaiagents (PyPI): upgrade to 1.6.78 or later
    pip install "praisonaiagents>=1.6.78"

Technical details

A vulnerability exists in the `AgentFlow._resolve_pydantic_class` method within `src/praisonai-agents/praisonaiagents/workflows/workflows.py`. When a workflow step utilizes a string-based `output_pydantic` reference, the framework automatically attempts to locate and import a sibling `tools.py` file from the workflow's directory using `importlib.util.exec_module`. This process occurs without sandboxing and bypasses existing security configurations like `PRAISONAI_ALLOW_*_TOOLS`. An attacker who can provide a malicious workflow file and a corresponding `tools.py` (e.g., via shared repositories or CI/CD artifacts) can achieve arbitrary Python code execution with the privileges of the workflow runner. The issue is addressed in version 1.6.78.

Affected products

  • MervinPraison (PraisonAI) praisonaiagents < 1.6.78

Identifiers

  • CVE-2026-61437
  • GHSA-4gfv-wg42-7jw5
  • PYSEC-2026-4267

Timeline

  • 2026-06-25: advisory: GitHub Security Advisory GHSA-4gfv-wg42-7jw5 published
  • 2026-07-10: disclosed: CVE-2026-61437 published to NVD
  • 2026-07-10: patched: Fix confirmed in version 1.6.78

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.