CVE-2026-55522: PraisonAI workflow include remote code execution in tools.py

CVE-2026-55522 · Severity: high · CVSS 7.8 · Published 2026-08-25

PraisonAI is an AI framework that orchestrates workflows and recipes. The workflow feature allows including other recipes as sub-steps. The vulnerability allows attackers to execute arbitrary Python code by placing a malicious `tools.py` file in a recipe directory that gets included in a workflow, even when the system is configured to disable automatic tool loading. This could allow an attacker with access to the workflow configuration or recipe files to run commands as the PraisonAI process user.

Technologies: praisonai (PyPI), praisonaiagents (PyPI). Vendors: PyPI.

Quick answers

Is CVE-2026-55522 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-55522 being exploited in the wild.
How severe is CVE-2026-55522?
High severity, with a CVSS score of 7.8, published 25 August 2026.
Which products and versions are affected?
praisonai (PyPI) ECOSYSTEM:introduced=3.9.26,fixed=4.6.58; praisonaiagents (PyPI) ECOSYSTEM:introduced=0.12.12,fixed=1.6.58.
Is there a fix for CVE-2026-55522?
Yes. praisonai (PyPI): upgrade to 4.6.58 or later; praisonaiagents (PyPI): upgrade to 1.6.58 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-55522 attacked?
It is attacked with local access.
Am I affected by CVE-2026-55522?
Check whether you run praisonai (PyPI) or 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

  • praisonai (PyPI): upgrade to 4.6.58 or later
    pip install "praisonai>=4.6.58"
  • praisonaiagents (PyPI): upgrade to 1.6.58 or later
    pip install "praisonaiagents>=1.6.58"

Technical details

The vulnerability exists in `praisonaiagents/workflows/workflows.py` in the `Workflow._execute_include()` method. When a workflow includes a recipe using the `Include` feature or YAML `include` directive, the code directly executes `importlib.util.spec_from_file_location()` followed by `spec.loader.exec_module()` on the recipe's `tools.py` file without checking the `PRAISONAI_ALLOW_TEMPLATE_TOOLS` or `PRAISONAI_ALLOW_LOCAL_TOOLS` environment variables that control tool autoloading elsewhere in the codebase. This allows module-level Python code to execute unconditionally during workflow initialization, before any LLM calls or child workflow parsing. The attack requires the attacker to control or influence a local recipe directory that is included in the victim's workflow, making exploitation possible in multi-tenant environments, CI/CD pipelines, or scenarios where workflows accept dynamic recipe paths. Patch available in version 4.6.58 for praisonaiagents and version 4.6.58 for praisonai.

Affected products

  • PraisonAI praisonaiagents >=0.12.12, <1.6.58
  • PraisonAI praisonai >=3.9.26, <4.6.58

Identifiers

  • CVE-2026-55522
  • GHSA-hxmv-c4g6-5fqc
  • PYSEC-2026-3891
  • PYSEC-2026-3903

Timeline

  • 2026-06-13: disclosed: Published on GitHub Advisory Database
  • 2026-08-25: patched: Fixed in praisonaiagents 1.6.58 and praisonai 4.6.58

References

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